Publications | Shape Vision Lab

2026

Preprint
Symmetry Matters: Auditing and Symmetrizing 3D Generative Models

N. Caytuiro and I. Sipiran

arXiv preprint arXiv:2503.02660, May 2026

Abs Bib PUBLICATION

Symmetry is a strong prior present in many object categories, yet standard benchmarks for 3D generative models rarely report whether this prior is preserved. We study symmetry preservation in unconditional point cloud generation. We first audit the symmetry of generated shapes by several 3D generative models and compute a normalized symmetry score based on the Chamfer Distance (CD). We show that although current 3D generative models achieve competitive results under standard evaluation, they reveal a persistent symmetry gap when a symmetry-aware evaluation protocol is applied. To test whether this gap is merely inherited from the training data, we evaluate these models over a mirrored-objects dataset derived from ShapeNet and analyze symmetry dynamics during training. Mechanistic interpretability techniques were employed at the sampling and latent levels to further show that reflection symmetry is not reliably encoded in the learned generative process. Finally, to address this gap, we propose a data-centric symmetry-aware intervention: training generative models on a half-objects dataset and reconstructing full objects by reflection during sampling. Across multiple backbones, this intervention substantially improves geometric consistency and visual plausibility while remaining competitive under standard metrics. These findings suggest that symmetry-aware evaluation is needed alongside standard benchmarks, and incoming 3D generative models should incorporate this prior explicitly, either during training or sampling.
@article{Caytuiro2026SymmetryMatters, title = {Symmetry Matters: Auditing and Symmetrizing 3D Generative Models}, author = {Caytuiro, N. and Sipiran, I.}, journal = {arXiv preprint arXiv:2503.02660}, %%location = {}, volume = {}, issue = {}, pages = {}, numpages = {12}, year = {2026}, month = may, publisher = {}, %doi = {}, }
WACV
Enhanced Back-Projection of Vision Features for 3D Symmetry Detection

I. Aguirre and I. Sipiran

2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2026

Abs Bib PUBLICATION

We propose two algorithms for 3D symmetry detection based on enhanced back-projection of vision features extracted from foundation vision models such as DINOv2. Our method enhances back-projection by rendering multiple views of 3D objects, extracting features, and projecting them onto the geometry with two key improvements–Fibonacci view sampling and view rotations–that increase robustness and accuracy. Using these features, we detect symmetry planes and axes through two dedicated algorithms. Experiments on ShapeNet show that our plane detection approach outperforms both traditional geometric and learning-based methods by a wide margin. The method is also efficient, running in seconds on a single 8GB GPU, making it practical for large-scale or real-world applications. Overall, our results demonstrate that enhanced back-projection of vision features offers a simple yet effective framework for solving fundamental 3D geometric problems such as symmetry detection. Code is available at https://github.com/Spulp/EnhancedBackProjection.
@article{Aguirre2026EnhancedBP, title = {Enhanced Back-Projection of Vision Features for 3D Symmetry Detection}, author = {Aguirre, I. and Sipiran, I.}, journal = {2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, %location = {}, volume = {}, issue = {}, pages = {66-76}, numpages = {}, year = {2026}, month = {}, publisher = {}, %doi = {}, }
IJCV
Symmetria: A Synthetic Dataset for Learning in Point Clouds

I. Sipiran, G. Santelices, L. Oyarzún, A. Ranieri, C. Romanengo, and 2 more authors

International Journal of Computer Vision, Jan 2026

Abs Bib PUBLICATION

Unlike image or text domains that benefit from an abundance of large-scale datasets, point cloud learning techniques frequently encounter limitations due to the scarcity of extensive datasets. To overcome this limitation, we present Symmetria, a formula-driven dataset that can be generated at any arbitrary scale. By construction, it ensures the absolute availability of precise ground truth, promotes data-efficient experimentation by requiring fewer samples, enables broad generalization across diverse geometric settings, and offers easy extensibility to new tasks and modalities. Using the concept of symmetry, we create shapes with known structure and high variability, enabling neural networks to learn point cloud features effectively. Our results demonstrate that this dataset is highly effective for point cloud self-supervised pre-training, yielding models with strong performance in downstream tasks such as classification and segmentation, which also show good few-shot learning capabilities. Additionally, our dataset can support fine-tuning models to classify real-world objects, highlighting our approach’s practical utility and application. We also introduce a challenging task for symmetry detection and provide a benchmark for baseline comparisons. A significant advantage of our approach is the public availability of the dataset, the accompanying code, and the ability to generate very large collections, promoting further research and innovation in point cloud learning.
@article{Sipiran2026Symmetria, title = {Symmetria: A Synthetic Dataset for Learning in Point Clouds}, author = {Sipiran, I. and Santelices, G. and Oyarzún, L. and Ranieri, A. and Romanengo, C. and Biasotti, S. and Falcidieno, B.}, journal = {International Journal of Computer Vision}, %location = {}, volume = {134}, issue = {70}, pages = {}, numpages = {}, year = {2026}, month = jan, publisher = {}, %doi = {https://doi.org/10.1007/s11263-025-02684-0}, }

2025

Preprint
3D Shape Generation: A Survey

N. Caytuiro and I. Sipiran

arXiv preprint arXiv:2503.02660, Jun 2025

Abs Bib PUBLICATION

Recent advances in deep learning have significantly transformed the field of 3D shape generation, enabling the synthesis of complex, diverse, and semantically meaningful 3D objects. This survey provides a comprehensive overview of the current state-of-the-art in 3D shape generation, organizing the discussion around three core components: shape representations, generative modeling approaches, and evaluation protocols. We begin by categorizing 3D representations into explicit, implicit, and hybrid setups, highlighting their structural properties, advantages, and limitations. Next, we review a wide range of generation methods, focusing on feedforward architectures. We further summarize commonly used datasets and evaluation metrics that assess fidelity, diversity, and realism of generated shapes. Finally, we identify open challenges and outline future research directions that could drive progress in controllable, efficient, and high-quality 3D shape generation. This survey aims to serve as a valuable reference for researchers and practitioners seeking a structured and in-depth understanding of this rapidly evolving field.
@article{Caytuiro20253DShapeGen, title = {3D Shape Generation: A Survey}, author = {Caytuiro, N. and Sipiran, I.}, journal = {arXiv preprint arXiv:2503.02660}, %location = {}, volume = {}, issue = {}, pages = {}, numpages = {}, year = {2025}, month = jun, publisher = {}, %doi = {}, }
C&G
SHREC 2025: Partial retrieval benchmark

B. I. Blokland, I. Aguirre, I. Sipiran, B. Bustos, S. Biasotti, and 1 more author

Computers & Graphics, 2025

Abs Bib PUBLICATION

Partial retrieval is a long-standing problem in the 3D Object Retrieval community. Its main difficulties arise from how to define 3D local descriptors in a way that makes them effective for partial retrieval and robust to common real-world issues, such as occlusion, noise, or clutter, when dealing with 3D data. This SHREC track is based on the newly proposed ShapeBench benchmark to evaluate the matching performance of local descriptors. We propose an experiment consisting of three increasing levels of difficulty, where we combine different filters to simulate real-world issues related to the partial retrieval task. Our main findings show that classic 3D local descriptors like Spin Image are robust to several of the tested filters (and their combinations), but more recent learned local descriptors like GeDI can be competitive for some specific filters. Finally, no 3D local descriptor was able to successfully handle the hardest level of difficulty.
@article{vanBlokland2025SHREC, title = {SHREC 2025: Partial retrieval benchmark}, author = {van Blokland, B. I. and Aguirre, I. and Sipiran, I. and Bustos, B. and Biasotti, S. and Palmieri, G.}, journal = {Computers & Graphics}, %location = {}, volume = {132}, issue = {}, pages = {}, numpages = {November}, year = {2025}, month = {}, publisher = {}, %doi = {https://doi.org/10.1016/j.cag.2025.104397}, }
SIBGRAPI
Symmetry Shape Analysis

I. Sipiran

Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI), 2025

Abs Bib PUBLICATION

Symmetry is a fundamental and pervasive property found in both natural and man-made objects, playing a key role in aesthetics, structure, and function. In computational domains, symmetry serves as a powerful cue for data compression, structure inference, and shape understanding. This work presents a comprehensive overview of symmetry analysis in 3D shapes, with a particular focus on computational methods for symmetry detection and their applications in diverse fields such as CAD, computer vision, medicine, archaeology, and 3D modeling. We provide formal definitions of exact, approximate, and partial symmetries in the context of rigid transformations, and we survey five major categories of detection approaches: transformation-based, correspondence-based, voting-based, optimization-based, and learning-based methods. Special emphasis is placed on recent deep learning techniques, which have significantly advanced the state of the art yet face challenges in generalization and robustness. Finally, we identify key open problems and future directions, including the need for richer and more varied datasets, better generalization of learning-based models, effective formulations for symmetry detection in incomplete data, and the integration of symmetry priors in generative modeling. Our analysis highlights both the progress and the limitations of current methods and aims to guide future research toward more principled and capable symmetry-aware systems.
@article{Sipiran2025SymmetrySA, title = {Symmetry Shape Analysis}, author = {Sipiran, I.}, journal = {Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI)}, %location = {}, volume = {}, issue = {}, pages = {}, numpages = {November}, year = {2025}, month = {}, publisher = {}, %doi = {10.1109/SIBGRAPI67909.2025.11223488}, }
Preprint
A Dataset-free Approach for Self-supervised Learning of 3D Reflectional Symmetries

I. Aguirre, I. Sipiran, and G. Montañana

arXiv preprint arXiv:2503.02660, Mar 2025

Abs Bib PUBLICATION

In this paper, we explore a self-supervised model that learns to detect the symmetry of a single object without requiring a dataset—relying solely on the input object itself. We hypothesize that the symmetry of an object can be determined by its intrinsic features, eliminating the need for large datasets during training. Additionally, we design a self-supervised learning strategy that removes the necessity of ground truth labels.
@article{Aguirre2025DatasetFree, title = {A Dataset-free Approach for Self-supervised Learning of 3D Reflectional Symmetries}, author = {Aguirre, I. and Sipiran, I. and Montañana, G.}, journal = {arXiv preprint arXiv:2503.02660}, %location = {}, volume = {}, issue = {}, pages = {}, numpages = {}, year = {2025}, month = mar, publisher = {}, %doi = {}, }
ESWA
Multi-Label Learning on Low Label Density Sets with Few Examples

M. Vergara, B. Bustos, I. Sipiran, T. Schreck, and S. Lengauer

Expert Systems With Applications, 2025

Abs Bib PUBLICATION

Multi-label learning has experienced an immense growth in the last years due to the multiple real-life applications to which it is applicable, such as the classification of protein functions, or musical genres, among others. This has led to the proposal of categories for multi-label classification (MLC) problems that seek to establish guidelines for the different configurations, given either by the quality or quantity of the labels, the number of examples for training, etc. Such is the case for the class of problems known as “Challenging MLC”, those in which the universe of labels incorporates obstacles either in terms of quality (erroneously assigned labels, unseen labels, etc.) or quantity (thousands or millions of labels). Different methods have been developed to address these cases, and yet few efforts have been directed towards the case where, despite having a large label universe, the number of examples is small (of the same order as the labels), thus posing a more complex scenario. In this paper, we examine one important real-world problem case — the labeling of Geometric surface patterns, appearing on pottery objects from the Classical era. As we will show, existing methods from the state of the art can provide baseline performance, but cannot yet comprehensively address this and similar application problems. We present and encompassing experimental comparison of state of the art methods, detailing advantages and problems. We contribute a processing pipeline that allows us to achieve effective classifications. Our work addresses the importance case when the universe of labels admits a feasible simplification through natural language processing (NLP) techniques and augmentation of visual training data. Based on an in-depth analysis of results, we propose practical guidelines on how to face similar problems, regarding both the selection of techniques and the analysis of results. We also identify pressing issues for current research to make multi-labeling more widely applicable and functional.
@article{Vergara2025MultiLabel, title = {Multi-Label Learning on Low Label Density Sets with Few Examples}, author = {Vergara, M. and Bustos, B. and Sipiran, I. and Schreck, T. and Lengauer, S.}, journal = {Expert Systems With Applications}, %location = {}, volume = {265}, issue = {}, pages = {125942}, numpages = {}, year = {2025}, month = {}, publisher = {Elsevier}, %doi = {10.1016/j.eswa.2024.125942}, }
IEEE Access
Land-Cover Semantic Segmentation for Very-High-Resolution Remote Sensing Imagery using Deep Transfer Learning and Active Contour Loss

M. Chicchón, F. Leon-Trujillo, I. Sipiran, and R. Madrid

IEEE Access, 2025

Abs Bib PUBLICATION

An accurate land-cover segmentation of very-high-resolution aerial images is essential for a wide range of applications, including urban planning and natural resource management. However, the automation of this process remains a challenge owing to the complexity of images, variability in land surface features, and noise. In this study, a method for training convolutional neural networks and transformers to perform land-cover segmentation on very-high-resolution aerial images in a regional context was proposed. We assessed the U-Net-scSE, FT-U-NetFormer, and DC-Swin architectures, incorporating transfer learning and active contour loss functions to improve performance on semantic segmentation tasks. Our experiments conducted using the OpenEarthMap dataset, which includes images from 44 countries, demonstrate the superior performance of U-Net-scSE models with the EfficientNet-V2-XL and MiT-B4 encoders, achieving an mIoU of over 0.80 on a test dataset of urban and rural images from Peru.
@article{Chicchon2025LandCover, title = {Land-Cover Semantic Segmentation for Very-High-Resolution Remote Sensing Imagery using Deep Transfer Learning and Active Contour Loss}, author = {Chicchón, M. and Leon-Trujillo, F. and Sipiran, I. and Madrid, R.}, journal = {IEEE Access}, %location = {}, volume = {13}, issue = {}, pages = {59007--59019}, numpages = {}, year = {2025}, month = {}, publisher = {IEEE}, %doi = {10.1109/ACCESS.2025.3556632}, }

2024

CACM

The Role of Computing in the Study of Latin American Cultural Heritage

I. Sipiran

Communications of the ACM, New York, Aug 2024

Abs Bib PUBLICATION

@article{Sipiran2024RoleComputing,
  title = {The Role of Computing in the Study of Latin American Cultural Heritage},
  author = {Sipiran, I.},
  journal = {Communications of the ACM},
  location = {New York},
  volume = {67},
  issue = {8},
  pages = {58--62},
  numpages = {},
  year = {2024},
  month = aug,
  publisher = {ACM},
  %doi = {10.1145/3653309},
}

VisComp

A Convolutional Architecture for 3D Model Embedding Using Image Views

A. Labrada, B. Bustos, and I. Sipiran

The Visual Computer, 2024

Abs Bib PUBLICATION

@article{Labrada2024Convolutional3D,
  title = {A Convolutional Architecture for 3D Model Embedding Using Image Views},
  author = {Labrada, A. and Bustos, B. and Sipiran, I.},
  journal = {The Visual Computer},
  %location = {},
  volume = {40},
  issue = {},
  pages = {1601--1615},
  numpages = {},
  year = {2024},
  month = {},
  publisher = {Springer},
  %doi = {10.1007/s00371-023-02872-4},
}

JOCCH
Repetitive Patterns Recognition in Textures of Ancient Peruvian Pottery

S. Sepulveda, B. Bustos, and I. Sipiran

ACM Journal on Computing and Cultural Heritage, 2024

Abs Bib PUBLICATION

We present a study and comparison of computer vision methods for the task of finding repetitive motifs in ancient Peruvian pottery. Under this context, the main difficulties for solving the task are that the motifs are in most cases highly repetitive, that the motifs corresponding to the same pattern are slightly different due to being hand-drawn, and that the amount of data available for training and testing purposes is scarce.
@article{Sepulveda2024RepetitivePatterns, title = {Repetitive Patterns Recognition in Textures of Ancient Peruvian Pottery}, author = {Sepulveda, S. and Bustos, B. and Sipiran, I.}, journal = {ACM Journal on Computing and Cultural Heritage}, %location = {}, volume = {17}, issue = {4}, pages = {55:1--55:16}, numpages = {}, year = {2024}, month = {}, publisher = {ACM}, %doi = {10.1145/3694789}, }

ECCV

Unsupervised Video Summarization: A Reconstruction Model with Proximal Gradient Methods

A. Alfaro and I. Sipiran

In ECCV Workshop on Traditional Computer Vision, 2024

Abs Bib PUBLICATION

@inproceedings{Alfaro2024UnsupervisedVideo,
  title = {Unsupervised Video Summarization: A Reconstruction Model with Proximal Gradient Methods},
  author = {Alfaro, A. and Sipiran, I.},
  booktitle = {ECCV Workshop on Traditional Computer Vision},
  %location = {},
  volume = {},
  issue = {},
  pages = {},
  numpages = {},
  year = {2024},
  month = {},
  publisher = {},
  %doi = {},
}

VISART
Cultural Heritage 3D Reconstruction with Diffusion Networks

P. Jaramillo and I. Sipiran

In ECCV Workshop on Vision for Art (VISART VII), 2024

Abs Bib PUBLICATION

This article explores the use of recent generative AI algorithms for repairing cultural heritage objects, leveraging a conditional diffusion model designed to reconstruct 3D point clouds effectively. Our study evaluates the model’s performance across general and cultural heritage-specific settings. Results indicate that, with considerations for object variability, the diffusion model can accurately reproduce cultural heritage geometries.
@inproceedings{Jaramillo2024CulturalHeritage, title = {Cultural Heritage 3D Reconstruction with Diffusion Networks}, author = {Jaramillo, P. and Sipiran, I.}, booktitle = {ECCV Workshop on Vision for Art (VISART VII)}, %location = {}, volume = {}, issue = {}, pages = {}, numpages = {}, year = {2024}, month = {}, publisher = {}, %doi = {}, }

3DOR

Self-distillation for Efficient Object-level Point Cloud Learning

Lucas Oyarzún, Iván Sipiran, and José M. Saavedra

In Eurographics Workshop on 3D Object Retrieval (3DOR), 2024

Abs Bib PUBLICATION

@inproceedings{Oyarzun2024SelfDistillation,
  title = {Self-distillation for Efficient Object-level Point Cloud Learning},
  author = {Oyarzún, Lucas and Sipiran, Iván and Saavedra, José M.},
  booktitle = {Eurographics Workshop on 3D Object Retrieval (3DOR)},
  %location = {},
  volume = {},
  issue = {},
  pages = {},
  numpages = {},
  year = {2024},
  month = {},
  publisher = {},
  %doi = {},
}

2023

AutCon

Large-scale Multi-unit Floor Plan Dataset for Architectural Plan Analysis and Recognition

Pablo N. Pizarro, Nancy Hitschfeld, and Iván Sipiran

Automation in Construction, Dec 2023

Abs Bib PUBLICATION

@article{Pizarro2023FloorPlanDataset,
  title = {Large-scale Multi-unit Floor Plan Dataset for Architectural Plan Analysis and Recognition},
  author = {Pizarro, Pablo N. and Hitschfeld, Nancy and Sipiran, Iván},
  journal = {Automation in Construction},
  %location = {},
  volume = {156},
  issue = {},
  pages = {105132},
  numpages = {},
  year = {2023},
  month = dec,
  publisher = {Elsevier},
  %doi = {10.1016/j.autcon.2023.105132},
}

IEEE Access

Semantic Segmentation of Fish and Underwater Environments Using Deep Convolutional Neural Networks and Learned Active Contours

Miguel Chicchón, Héctor Bedón, Carlos R. Del-Blanco, and Iván Sipiran

IEEE Access, 2023

Abs Bib PUBLICATION

@article{Chicchon2023UnderwaterSegmentation,
  title = {Semantic Segmentation of Fish and Underwater Environments Using Deep Convolutional Neural Networks and Learned Active Contours},
  author = {Chicchón, Miguel and Bedón, Héctor and Del-Blanco, Carlos R. and Sipiran, Iván},
  journal = {IEEE Access},
  %location = {},
  volume = {11},
  issue = {},
  pages = {33652--33665},
  numpages = {},
  year = {2023},
  month = {},
  publisher = {IEEE},
  %doi = {},
}

3DOR

SHREC 2023: Detection of Symmetries on 3D Point Clouds Representing Simple Shapes

Iván Sipiran, Chiara Romanengo, Bianca Falcidieno, Silvia Biasotti, Gerasimos Arvanitis, and 11 more authors

In Eurographics Workshop on 3D Object Retrieval (3DOR), 2023

Abs Bib PUBLICATION

@inproceedings{Sipiran2023SHREC,
  title = {SHREC 2023: Detection of Symmetries on 3D Point Clouds Representing Simple Shapes},
  author = {Sipiran, Iván and Romanengo, Chiara and Falcidieno, Bianca and Biasotti, Silvia and Arvanitis, Gerasimos and Chen, Chen and Fotis, Vlassis and He, Jianfang and Lv, Xiaoling and Moustakas, Konstantinos and Peng, Silong and Romanelis, Ioannis and Sun, Wenhao and Vlachos, Christoforos and Wu, Ziyu and Xie, Qiong},
  booktitle = {Eurographics Workshop on 3D Object Retrieval (3DOR)},
  %location = {},
  volume = {},
  issue = {},
  pages = {},
  numpages = {},
  year = {2023},
  month = {},
  publisher = {},
  %doi = {},
}

JWSCG

Visual Exploration of Repetitive Patterns on Ancient Peruvian Pottery

Stefan Lengauer, Lin Shao, Magdalena Mayerhofer, Reinhold Preiner, Stephan Karl, and 4 more authors

Journal of WSCG, Nov 2023

Abs Bib PUBLICATION

@article{Lengauer2023VisualExploration,
  title = {Visual Exploration of Repetitive Patterns on Ancient Peruvian Pottery},
  author = {Lengauer, Stefan and Shao, Lin and Mayerhofer, Magdalena and Preiner, Reinhold and Karl, Stephan and Trinkl, Elisabeth and Sipiran, Iván and Bustos, Benjamin and Schreck, Tobias},
  journal = {Journal of WSCG},
  %location = {},
  volume = {31},
  issue = {1-2},
  pages = {25--33},
  numpages = {},
  year = {2023},
  month = nov,
  publisher = {},
  %doi = {10.24132/JWSCG.2023.3},
}

ICCVW

MatchMakerNet: Enabling Fragment Matching for Cultural Heritage Analysis

Ariana M. Villegas-Suarez, Cristian Lopez, and Iván Sipiran

In Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2023

Abs Bib PUBLICATION

@inproceedings{Villegas2023MatchMakerNet,
  title = {MatchMakerNet: Enabling Fragment Matching for Cultural Heritage Analysis},
  author = {Villegas-Suarez, Ariana M. and Lopez, Cristian and Sipiran, Iván},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)},
  %location = {},
  volume = {},
  issue = {},
  pages = {},
  numpages = {},
  year = {2023},
  month = {},
  publisher = {},
  %doi = {},
}

ICCVW

Evaluation of 3D Reconstruction for Cultural Heritage Applications

Cristián Llull, Nelson Baloian, Benjamin Bustos, Kornelius Kupczik, Iván Sipiran, and 1 more author

In Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Oct 2023

Abs Bib PUBLICATION

@inproceedings{Llull2023Evaluation3DReconstruction,
  title = {Evaluation of 3D Reconstruction for Cultural Heritage Applications},
  author = {Llull, Cristián and Baloian, Nelson and Bustos, Benjamin and Kupczik, Kornelius and Sipiran, Iván and Baloian, Andrés},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)},
  %location = {},
  volume = {},
  issue = {},
  pages = {1634--1643},
  numpages = {},
  year = {2023},
  month = oct,
  publisher = {IEEE},
  %doi = {10.1109/ICCVW60793.2023.00179},
}

2022

IJCV

Data-Driven Restoration of Digital Archaeological Pottery with Point Cloud Analysis

Iván Sipiran, Alexis Mendoza, Alexander Apaza, and Cristian Lopez

International Journal of Computer Vision, Sep 2022

Abs Bib PUBLICATION

@article{Sipiran2022DataDrivenRestoration,
  title = {Data-Driven Restoration of Digital Archaeological Pottery with Point Cloud Analysis},
  author = {Sipiran, Iván and Mendoza, Alexis and Apaza, Alexander and Lopez, Cristian},
  journal = {International Journal of Computer Vision},
  %location = {},
  volume = {130},
  issue = {9},
  pages = {2149--2165},
  numpages = {},
  year = {2022},
  month = sep,
  publisher = {Springer},
  %doi = {10.1007/s11263-022-01637-1},
}

CompGraph

SHREC 2022: Fitting and Recognition of Simple Geometric Primitives on Point Clouds

Chiara Romanengo, Andrea Raffo, Silvia Biasotti, Bianca Falcidieno, Vlassis Fotis, and 15 more authors

Computers & Graphics, Oct 2022

Abs Bib PUBLICATION

@article{Romanengo2022SHREC,
  title = {SHREC 2022: Fitting and Recognition of Simple Geometric Primitives on Point Clouds},
  author = {Romanengo, Chiara and Raffo, Andrea and Biasotti, Silvia and Falcidieno, Bianca and Fotis, Vlassis and Romanelis, Ioannis and Psatha, Eleftheria and Moustakas, Konstantinos and Sipiran, Iván and Nguyen, Quang-Thuc and Chu, Chi-Bien and Nguyen-Ngoc, Khoi and Vo, Dinh-Khoi and To, Tuan-An and Nguyen, Nham-Tan and Le-Pham, Nhat-Quynh and Nguyen, Hai-Dang and Tran, Minh-Triet and Qie, Yifan and Anwer, Nabil},
  journal = {Computers & Graphics},
  %location = {},
  volume = {107},
  issue = {},
  pages = {32--49},
  numpages = {},
  year = {2022},
  month = oct,
  publisher = {Elsevier},
  %doi = {10.1016/j.cag.2022.07.004},
}

CompGraph

SHREC 2022: Pothole and Crack Detection in the Road Pavement Using Images and RGB-D Data

Elia Moscoso Thompson, Andrea Ranieri, Silvia Biasotti, Miguel Chicchón, Iván Sipiran, and 4 more authors

Computers & Graphics, Oct 2022

Abs Bib PUBLICATION

@article{Thompson2022SHREC,
  title = {SHREC 2022: Pothole and Crack Detection in the Road Pavement Using Images and RGB-D Data},
  author = {Thompson, Elia Moscoso and Ranieri, Andrea and Biasotti, Silvia and Chicchón, Miguel and Sipiran, Iván and Pham, Minh-Khoi and Nguyen-Ho, Thang-Long and Nguyen, Hai-Dang and Tran, Minh-Triet},
  journal = {Computers & Graphics},
  %location = {},
  volume = {107},
  issue = {},
  pages = {161--171},
  numpages = {},
  year = {2022},
  month = oct,
  publisher = {Elsevier},
  %doi = {10.1016/j.cag.2022.07.018},
}

AutCon

Automatic Floor Plan Analysis and Recognition

Pablo N. Pizarro, Nancy Hitschfeld, Iván Sipiran, and José M. Saavedra

Automation in Construction, Aug 2022

Abs Bib PUBLICATION

@article{Pizarro2022FloorPlan,
  title = {Automatic Floor Plan Analysis and Recognition},
  author = {Pizarro, Pablo N. and Hitschfeld, Nancy and Sipiran, Iván and Saavedra, José M.},
  journal = {Automation in Construction},
  %location = {},
  volume = {140},
  issue = {},
  pages = {104348},
  numpages = {},
  year = {2022},
  month = aug,
  publisher = {Elsevier},
  %doi = {10.1016/j.autcon.2022.104348},
}

AIRev

A Comprehensive Review of the Video-to-Text Problem

Jesús Perez-Martin, Benjamin Bustos, Silvio Jamil F. Guimarães, Iván Sipiran, Jorge Pérez, and 1 more author

Artificial Intelligence Review, May 2022

Abs Bib PUBLICATION

@article{PerezMartin2022VideoToText,
  title = {A Comprehensive Review of the Video-to-Text Problem},
  author = {Perez-Martin, Jesús and Bustos, Benjamin and Guimarães, Silvio Jamil F. and Sipiran, Iván and Pérez, Jorge and Coello, Grethel},
  journal = {Artificial Intelligence Review},
  %location = {},
  volume = {55},
  issue = {5},
  pages = {4165--4239},
  numpages = {},
  year = {2022},
  month = may,
  publisher = {Springer},
  %doi = {10.1007/s10462-021-10104-1},
}

Interactive Annotation of Geometric Ornamentation on Painted Pottery Assisted by Deep Learning

Stefan Lengauer, Peter Houska, Reinhold Preiner, Elisabeth Trinkl, Stephan Karl, and 3 more authors

it - Information Technology, Aug 2022

Abs Bib PUBLICATION

@article{Lengauer2022InteractiveAnnotation,
  title = {Interactive Annotation of Geometric Ornamentation on Painted Pottery Assisted by Deep Learning},
  author = {Lengauer, Stefan and Houska, Peter and Preiner, Reinhold and Trinkl, Elisabeth and Karl, Stephan and Sipiran, Iván and Bustos, Benjamin and Schreck, Tobias},
  journal = {it - Information Technology},
  %location = {},
  volume = {64},
  issue = {6},
  pages = {217--231},
  numpages = {},
  year = {2022},
  month = aug,
  publisher = {De Gruyter},
  %doi = {10.1515/itit-2022-0007},
}

GCH

Context-Based Surface Pattern Completion of Ancient Pottery

Stefan Lengauer, Reinhold Preiner, Iván Sipiran, Stephan Karl, Elisabeth Trinkl, and 2 more authors

In Proceedings of the Eurographics Workshop on Graphics and Cultural Heritage, 2022

Abs Bib PUBLICATION

@inproceedings{Lengauer2022ContextBased,
  title = {Context-Based Surface Pattern Completion of Ancient Pottery},
  author = {Lengauer, Stefan and Preiner, Reinhold and Sipiran, Iván and Karl, Stephan and Trinkl, Elisabeth and Bustos, Benjamin and Schreck, Tobias},
  booktitle = {Proceedings of the Eurographics Workshop on Graphics and Cultural Heritage},
  %location = {},
  volume = {},
  issue = {},
  pages = {107--115},
  numpages = {},
  year = {2022},
  month = {},
  publisher = {Eurographics Association},
  %doi = {10.2312/gch.20221234},
}

2021

CompGraph

SHREC 2021: Retrieval of Cultural Heritage Objects

Iván Sipiran, Patrick Lazo, Cristian Lopez, Mauricio Jimenez, Nikhil Bagewadi, and 21 more authors

Computers & Graphics, Nov 2021

Abs Bib PUBLICATION

@article{Sipiran2021SHREC,
  title = {SHREC 2021: Retrieval of Cultural Heritage Objects},
  author = {Sipiran, Iván and Lazo, Patrick and Lopez, Cristian and Jimenez, Mauricio and Bagewadi, Nikhil and Bustos, Benjamin and Dao, Huy and Gangisetty, Suman and Hanik, Marek and Ho-Thi, Nguyen-Phuong and Holenderski, Maciej and Jarnikov, Dmitri and Labrada, Andrés and Licandro, Rodrigo and Nguyen, Dinh-Hoang and Nguyen-Ho, Thang-Long and Perez-Rey, Luis A. and Pham, Binh-Dang and Pham, Minh-Khoi and Preiner, Reinhold and Schreck, Tobias and Trinh, Quang-Huy and Tonnaer, Laurens and von Tycowicz, Christoph and Vu-Le, Tuan-Anh and Lengauer, Stefan},
  journal = {Computers & Graphics},
  %location = {},
  volume = {100},
  issue = {},
  pages = {1--20},
  numpages = {},
  year = {2021},
  month = nov,
  publisher = {Elsevier},
  %doi = {10.1016/j.cag.2021.07.010},
}

CGF

A Benchmark Dataset for Repetitive Pattern Recognition on Textured 3D Surfaces

Stefan Lengauer, Iván Sipiran, Reinhold Preiner, Tobias Schreck, and Benjamin Bustos

Computer Graphics Forum, 2021

Abs Bib PUBLICATION

@article{Lengauer2021BenchmarkDataset,
  title = {A Benchmark Dataset for Repetitive Pattern Recognition on Textured 3D Surfaces},
  author = {Lengauer, Stefan and Sipiran, Iván and Preiner, Reinhold and Schreck, Tobias and Bustos, Benjamin},
  journal = {Computer Graphics Forum},
  %location = {},
  volume = {40},
  issue = {5},
  pages = {},
  numpages = {},
  year = {2021},
  month = {},
  publisher = {Wiley},
  %doi = {10.1111/cgf.14352},
}

2020

CompGraph

SHREC’20 Track: Retrieval of Digital Surfaces with Similar Geometric Reliefs

E. Moscoso, S. Biasotti, A. Giachetti, C. Tortorici, N. Werghi, and 21 more authors

Computers & Graphics, Oct 2020

Abs Bib PUBLICATION

@article{Moscoso2020SHREC,
  title = {SHREC’20 Track: Retrieval of Digital Surfaces with Similar Geometric Reliefs},
  author = {Moscoso, E. and Biasotti, S. and Giachetti, A. and Tortorici, C. and Werghi, N. and Shaker, A. and Berretti, S. and Nguyen-Dinh, H. and Le, M. and Nguyen, H. and Tran, M. and Gigli, L. and Velasco-Forero, S. and Marcotegui, B. and Sipiran, I. and Bustos, B. and Romanelis, I. and Fotis, V. and Arvanitis, G. and Moustakas, K. and Otu, E. and Zwiggelaar, R. and Hunter, D. and Liu, Y. and Arteaga, Y. and Luxman, R.},
  journal = {Computers & Graphics},
  %location = {},
  volume = {91},
  issue = {},
  pages = {199--218},
  numpages = {},
  year = {2020},
  month = oct,
  publisher = {Elsevier},
  %doi = {10.1016/j.cag.2020.07.005},
}

3DImaging

3D Shape Matching for Retrieval and Recognition

Benjamin Bustos and Iván Sipiran

In 3D Imaging, Analysis and Applications, 2020

Abs Bib PUBLICATION

@incollection{Bustos2020ShapeMatching,
  title = {3D Shape Matching for Retrieval and Recognition},
  author = {Bustos, Benjamin and Sipiran, Iván},
  booktitle = {3D Imaging, Analysis and Applications},
  %location = {},
  volume = {},
  issue = {},
  pages = {413--461},
  numpages = {},
  year = {2020},
  month = {},
  publisher = {Springer},
  %doi = {10.1007/978-3-030-44070-1_9},
}

GCH

Semi-automated Annotation of Repetitive Ornaments on 3D Painted Pottery Surfaces

Stefan Lengauer, Alexander Komar, Stephan Karl, Elisabeth Trinkl, Iván Sipiran, and 2 more authors

In Proceedings of the Eurographics Workshop on Graphics and Cultural Heritage, Nov 2020

Abs Bib PUBLICATION

@inproceedings{Lengauer2020Annotation,
  title = {Semi-automated Annotation of Repetitive Ornaments on 3D Painted Pottery Surfaces},
  author = {Lengauer, Stefan and Komar, Alexander and Karl, Stephan and Trinkl, Elisabeth and Sipiran, Iván and Schreck, Tobias and Preiner, Reinhold},
  booktitle = {Proceedings of the Eurographics Workshop on Graphics and Cultural Heritage},
  %location = {},
  volume = {},
  issue = {},
  pages = {},
  numpages = {},
  year = {2020},
  month = nov,
  publisher = {Eurographics Association},
  %doi = {10.2312/gch.20201285},
}

2018

3DOR

Completion of Cultural Heritage Objects with Rotational Symmetry

Iván Sipiran

In Eurographics Workshop on 3D Object Retrieval (3DOR), Apr 2018

Abs Bib PUBLICATION

@inproceedings{Sipiran2018Completion,
  title = {Completion of Cultural Heritage Objects with Rotational Symmetry},
  author = {Sipiran, Iván},
  booktitle = {Eurographics Workshop on 3D Object Retrieval (3DOR)},
  %location = {},
  volume = {},
  issue = {},
  pages = {87--93},
  numpages = {},
  year = {2018},
  month = apr,
  publisher = {Eurographics Association},
  %doi = {10.2312/3dor.20182004},
}

CGI

3D Reconstruction of Incomplete Archaeological Objects Using a Generative Adversarial Network

Renato Hermoza and Iván Sipiran

In Proceedings of Computer Graphics International (CGI), Jun 2018

Abs Bib PUBLICATION

@inproceedings{Hermoza2018GAN,
  title = {3D Reconstruction of Incomplete Archaeological Objects Using a Generative Adversarial Network},
  author = {Hermoza, Renato and Sipiran, Iván},
  booktitle = {Proceedings of Computer Graphics International (CGI)},
  %location = {},
  volume = {},
  issue = {},
  pages = {},
  numpages = {},
  year = {2018},
  month = jun,
  publisher = {ACM},
  %doi = {10.1145/3208159.3208173},
}

2017

VisComp
Scalable 3D Shape Retrieval Using Local Features and the Signature Quadratic Form Distance

I. Sipiran, J. Lokoc, B. Bustos, and T. Skopal

The Visual Computer, 2017

Abs Bib PUBLICATION

We present a scalable and unsupervised approach for content-based retrieval on 3D model collections. Our goal is to represent a 3D shape as a set of discriminative local features, which is important to maintain robustness against deformations such as non-rigid transformations and partial data. However, this representation brings up the problem on how to compare two 3D models represented by feature sets. For solving this problem, we apply the signature quadratic form distance (SQFD), which is suitable for comparing feature sets.
@article{Sipiran2017Scalable3D, title = {Scalable 3D Shape Retrieval Using Local Features and the Signature Quadratic Form Distance}, author = {Sipiran, I. and Lokoc, J. and Bustos, B. and Skopal, T.}, journal = {The Visual Computer}, %location = {}, volume = {33}, issue = {12}, pages = {1571--1585}, numpages = {}, year = {2017}, month = {}, publisher = {Springer}, %doi = {10.1007/s00371-016-1301-5}, }
JOCCH
From Reassembly to Object Completion - A Complete Systems Pipeline

G. Papaioannou, T. Schreck, A. Andreadis, P. Mavridis, R. Gregor, and 2 more authors

ACM Journal on Computing and Cultural Heritage, Feb 2017

Abs Bib PUBLICATION

The problem of the restoration of broken artifacts, where large parts could be missing, is of high importance in archaeology. The typical manual restoration can become a tedious and error-prone process, which also does not scale well. In recent years, many methods have been proposed for assisting the process, most of which target specialized object types or operate under very strict constraints.
@article{Papaioannou2017Reassembly, title = {From Reassembly to Object Completion - A Complete Systems Pipeline}, author = {Papaioannou, G. and Schreck, T. and Andreadis, A. and Mavridis, P. and Gregor, R. and Sipiran, I. and Vardis, K.}, journal = {ACM Journal on Computing and Cultural Heritage}, %location = {}, volume = {10}, issue = {2}, pages = {8:1--8:22}, numpages = {}, year = {2017}, month = feb, publisher = {ACM}, %doi = {10.1145/3009905}, }

ICCVW

Analysis of Partial Axial Symmetry on 3D Surfaces and Its Application in the Restoration of Cultural Heritage Objects

I. Sipiran

In Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCVW), Oct 2017

Abs Bib PUBLICATION

@inproceedings{Sipiran2017PartialSymmetry,
  title = {Analysis of Partial Axial Symmetry on 3D Surfaces and Its Application in the Restoration of Cultural Heritage Objects},
  author = {Sipiran, I.},
  booktitle = {Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCVW)},
  %location = {},
  volume = {},
  issue = {},
  pages = {2925--2933},
  numpages = {},
  year = {2017},
  month = oct,
  publisher = {IEEE},
  %doi = {10.1109/ICCVW.2017.343},
}

3DOR

SHREC’17 Track: Point-Cloud Shape Retrieval of Non-Rigid Toys

F. A. Limberger, R. C. Wilson, M. Aono, N. Audebert, A. Boulch, and 13 more authors

In Eurographics Workshop on 3D Object Retrieval (3DOR), Apr 2017

Abs Bib PUBLICATION

@inproceedings{Limberger2017SHREC,
  title = {SHREC'17 Track: Point-Cloud Shape Retrieval of Non-Rigid Toys},
  author = {Limberger, F. A. and Wilson, R. C. and Aono, M. and Audebert, N. and Boulch, A. and Bustos, B. and Giachetti, A. and Godil, A. and Le Saux, B. and Li, B. and Lu, Y. and Nguyen, H. D. and Nguyen, V. T. and Pham, V. K. and Sipiran, I. and Tatsuma, A. and Tran, M. T. and Velasco-Forero, S.},
  booktitle = {Eurographics Workshop on 3D Object Retrieval (3DOR)},
  %location = {},
  volume = {},
  issue = {},
  pages = {75--84},
  numpages = {},
  year = {2017},
  month = apr,
  publisher = {Eurographics Association},
  %doi = {10.2312/3dor.20171056},
}

3DOR

SHREC’17 Track: Retrieval of Surfaces with Similar Relief Patterns

S. Biasotti, E. Moscoso Thompson, M. Aono, A. Ben Hamza, B. Bustos, and 17 more authors

In Eurographics Workshop on 3D Object Retrieval (3DOR), Apr 2017

Abs Bib PUBLICATION

This paper presents the results of the SHREC’17 contest on retrieval of surfaces with similar relief patterns. The proposed task was created in order to verify the possibility of retrieving surface patches with a relief pattern similar to an example from a database of small surface elements.

@inproceedings{Biasotti2017SHREC,
  title = {SHREC'17 Track: Retrieval of Surfaces with Similar Relief Patterns},
  author = {Biasotti, S. and Moscoso Thompson, E. and Aono, M. and Ben Hamza, A. and Bustos, B. and Dong, S. and Du, B. and Fehri, A. and Li, H. and Limberger, F. A. and Masoumi, M. and Rezaei, M. and Sipiran, I. and Sun, L. and Tatsuma, A. and Velasco Forero, S. and Wilson, R. C. and Wu, Y. and Zhang, J. and Zhao, T. and Fornasa, F. and Giachetti, A.},
  booktitle = {Eurographics Workshop on 3D Object Retrieval (3DOR)},
  %location = {},
  volume = {},
  issue = {},
  pages = {95--103},
  numpages = {},
  year = {2017},
  month = apr,
  publisher = {Eurographics Association},
  %doi = {10.2312/3dor.20171058},
}

2016

JVLC

Guiding the Exploration of Scatter Plot Data Using Motif-Based Interest Measures

L. Shao, T. Schleicher, M. Behrisch, T. Schreck, I. Sipiran, and 1 more author

Journal of Visual Languages and Computing, 2016

Abs Bib PUBLICATION

@article{Shao2016ScatterPlot,
  title = {Guiding the Exploration of Scatter Plot Data Using Motif-Based Interest Measures},
  author = {Shao, L. and Schleicher, T. and Behrisch, M. and Schreck, T. and Sipiran, I. and Keim, D. A.},
  journal = {Journal of Visual Languages and Computing},
  %location = {},
  volume = {36},
  issue = {},
  pages = {1--12},
  numpages = {},
  year = {2016},
  month = {},
  publisher = {Elsevier},
  %doi = {10.1016/j.jvlc.2016.07.003},
}

2015

CGF

Object Completion Using k-Sparse Optimization

P. Mavridis, I. Sipiran, A. Andreadis, and G. Papaioannou

Computer Graphics Forum, Oct 2015

Abs Bib PUBLICATION

@article{Mavridis2015kSparse,
  title = {Object Completion Using k-Sparse Optimization},
  author = {Mavridis, P. and Sipiran, I. and Andreadis, A. and Papaioannou, G.},
  journal = {Computer Graphics Forum},
  %location = {},
  volume = {34},
  issue = {7},
  pages = {13--21},
  numpages = {},
  year = {2015},
  month = oct,
  publisher = {Wiley},
  %doi = {10.1111/cgf.12741},
}

SIGGRAPH
Fractured 3D Object Restoration and Completion

A. Andreadis, R. Gregor, I. Sipiran, P. Mavridis, G. Papaioannou, and 1 more author

In ACM SIGGRAPH 2015 Posters, Los Angeles, CA, USA, Aug 2015

Abs Bib PUBLICATION

We introduce a pipeline for restoration of 3D shapes based on reassembly of fragments and completion of missing parts. First results show the effectiveness of the approach for restoration of real-world fragment data from the Cultural Heritage domain.
@inproceedings{Andreadis2015Fractured, title = {Fractured 3D Object Restoration and Completion}, author = {Andreadis, A. and Gregor, R. and Sipiran, I. and Mavridis, P. and Papaioannou, G. and Schreck, T.}, booktitle = {ACM SIGGRAPH 2015 Posters}, location = {Los Angeles, CA, USA}, volume = {}, issue = {}, pages = {}, numpages = {}, year = {2015}, month = aug, publisher = {ACM}, %doi = {10.1145/2787626.2792633}, }
CBMI
Empirical Evaluation of Dissimilarity Measures for 3D Object Retrieval with Application to Multi-Feature Retrieval

R. Gregor, A. Lamprecht, I. Sipiran, T. Schreck, and B. Bustos

In Proceedings of the 13th International Workshop on Content-Based Multimedia Indexing (CBMI), Prague, Czech Republic, Jun 2015

Abs Bib PUBLICATION

We provide an extensive comparison of dissimilarity measures for 3D object retrieval. Our study is based on an encompassing set of feature extractors, dissimilarity measures, and benchmark data sets. We identify the best performing dissimilarity measures and in turn identify dependencies between well-performing dissimilarity measures and types of 3D features.
@inproceedings{Gregor2015Empirical, title = {Empirical Evaluation of Dissimilarity Measures for 3D Object Retrieval with Application to Multi-Feature Retrieval}, author = {Gregor, R. and Lamprecht, A. and Sipiran, I. and Schreck, T. and Bustos, B.}, booktitle = {Proceedings of the 13th International Workshop on Content-Based Multimedia Indexing (CBMI)}, location = {Prague, Czech Republic}, volume = {}, issue = {}, pages = {1--6}, numpages = {}, year = {2015}, month = jun, publisher = {IEEE}, %doi = {10.1109/CBMI.2015.7153629}, }

3DOR

SHREC’15: Range Scans Based 3D Shape Retrieval

A. Godil, H. Dutagaci, B. Bustos, S. Choi, S. Dong, and 12 more authors

In Eurographics Workshop on 3D Object Retrieval (3DOR), Zurich, Switzerland, May 2015

Abs Bib PUBLICATION

@inproceedings{Godil2015SHREC,
  title = {SHREC'15: Range Scans Based 3D Shape Retrieval},
  author = {Godil, A. and Dutagaci, H. and Bustos, B. and Choi, S. and Dong, S. and Furuya, T. and Li, H. and Link, N. and Moriyama, A. and Meruane, R. and Ohbuchi, R. and Paulus, D. and Schreck, T. and Seib, V. and Sipiran, I. and Yin, H. and Zhang, C.},
  booktitle = {Eurographics Workshop on 3D Object Retrieval (3DOR)},
  location = {Zurich, Switzerland},
  volume = {},
  issue = {},
  pages = {153--160},
  numpages = {},
  year = {2015},
  month = may,
  publisher = {Eurographics Association},
  %doi = {10.2312/3dor.20151066},
}

3DOR

SHREC’15: Scalability of Non-Rigid 3D Shape Retrieval

I. Sipiran, B. Bustos, T. Schreck, A. Bronstein, S. Choi, and 4 more authors

In Eurographics Workshop on 3D Object Retrieval (3DOR), Zurich, Switzerland, May 2015

Abs Bib PUBLICATION

@inproceedings{Sipiran2015SHREC,
  title = {SHREC'15: Scalability of Non-Rigid 3D Shape Retrieval},
  author = {Sipiran, I. and Bustos, B. and Schreck, T. and Bronstein, A. and Choi, S. and Lai, L. and Li, H. and Litman, R. and Sun, L.},
  booktitle = {Eurographics Workshop on 3D Object Retrieval (3DOR)},
  location = {Zurich, Switzerland},
  volume = {},
  issue = {},
  pages = {121--128},
  numpages = {},
  year = {2015},
  month = may,
  publisher = {Eurographics Association},
  %doi = {10.2312/3dor.20151065},
}

3DOR

Automatic 3D Object Fracturing for Evaluation of Partial Retrieval and Object Restoration Tasks - Benchmark and Application to 3D Cultural Heritage Data

R. Gregor, D. Bauer, I. Sipiran, P. Perakis, and T. Schreck

In Eurographics Workshop on 3D Object Retrieval (3DOR), Zurich, Switzerland, May 2015

Abs Bib PUBLICATION

@inproceedings{Gregor2015Automatic,
  title = {Automatic 3D Object Fracturing for Evaluation of Partial Retrieval and Object Restoration Tasks - Benchmark and Application to 3D Cultural Heritage Data},
  author = {Gregor, R. and Bauer, D. and Sipiran, I. and Perakis, P. and Schreck, T.},
  booktitle = {Eurographics Workshop on 3D Object Retrieval (3DOR)},
  location = {Zurich, Switzerland},
  volume = {},
  issue = {},
  pages = {7--14},
  numpages = {},
  year = {2015},
  month = may,
  publisher = {Eurographics Association},
  %doi = {10.2312/3dor.20151049},
}

2014

BDVC

Quality Metrics Driven Approach to Visualize Multidimensional Data in Scatterplot Matrix

M. Behrisch, L. Shao, B. C. Kwon, T. Schreck, I. Sipiran, and 1 more author

In GI Workshop Big Data Visual Computing – Quantitative Perspectives for Visual Computing, Stuttgart, Germany, Sep 2014

Abs Bib PUBLICATION

@inproceedings{Behrisch2014Quality,
  title = {Quality Metrics Driven Approach to Visualize Multidimensional Data in Scatterplot Matrix},
  author = {Behrisch, M. and Shao, L. and Kwon, B. C. and Schreck, T. and Sipiran, I. and Keim, D. A.},
  booktitle = {GI Workshop Big Data Visual Computing – Quantitative Perspectives for Visual Computing},
  location = {Stuttgart, Germany},
  volume = {},
  issue = {},
  pages = {},
  numpages = {},
  year = {2014},
  month = sep,
  publisher = {Gesellschaft für Informatik},
  %doi = {},
}

BDVC
Identifying Locally Interesting Motifs for Exploration of Scatter Plot Matrices

L. Shao, M. Behrisch, T. Schreck, I. Sipiran, B. C. Kwon, and 1 more author

In GI Workshop Big Data Visual Computing – Quantitative Perspectives for Visual Computing, Stuttgart, Germany, Sep 2014

Abs Bib PUBLICATION

We present a preliminary idea to explore the scatter plot space by identifying significant local patterns (also called motifs in this work). Based on certain clustering algorithms and image-based descriptors, we identify and group a set of similar local candidate motifs in a large scatter plot space.
@inproceedings{Shao2014Identifying, title = {Identifying Locally Interesting Motifs for Exploration of Scatter Plot Matrices}, author = {Shao, L. and Behrisch, M. and Schreck, T. and Sipiran, I. and Kwon, B. C. and Keim, D. A.}, booktitle = {GI Workshop Big Data Visual Computing – Quantitative Perspectives for Visual Computing}, location = {Stuttgart, Germany}, volume = {}, issue = {}, pages = {}, numpages = {}, year = {2014}, month = sep, publisher = {Gesellschaft für Informatik}, %doi = {}, }

2013

VisComput
Key-components: Detection of salient regions on 3D meshes

Ivan Sipiran and Benjamin Bustos

The Visual Computer, Dec 2013

Abs Bib PUBLICATION

In this paper, we present a method to detect stable components on 3D meshes. A component is a salient region on the mesh which contains discriminative local features. Our goal is to represent a 3D mesh with a set of regions, which we called key-components, that characterize the represented object and therefore, they could be used for effective matching and recognition. As key-components are features in coarse scales, they are less sensitive to mesh deformations such as noise.
@article{sipiran2013keycomponents, title = {Key-components: Detection of salient regions on 3D meshes}, author = {Sipiran, Ivan and Bustos, Benjamin}, journal = {The Visual Computer}, %location = {}, volume = {29}, issue = {12}, pages = {1319--1332}, numpages = {14}, year = {2013}, month = dec, publisher = {Springer}, %doi = {10.1007/s00371-013-0870-9}, }
ICCV
A Fully Hierarchical Approach for Finding Correspondences in Non-rigid Shapes

Ivan Sipiran and Benjamin Bustos

In Proceedings of the IEEE International Conference on Computer Vision (ICCV), Sydney, Australia, Dec 2013

Abs Bib PUBLICATION

This paper presents a hierarchical method for finding correspondences in non-rigid shapes. We propose a new representation for 3D meshes: the decomposition tree. This structure characterizes the recursive decomposition process of a mesh into regions of interest and keypoints. We also propose a hierarchical matching algorithm that performs in a level-wise manner. The matching process is guided by the similarity between regions in high levels of the tree, until reaching the keypoints stored in the leaves. This allows us to reduce the search space of correspondences, making also the matching process efficient.
@inproceedings{sipiran2013hierarchical, title = {A Fully Hierarchical Approach for Finding Correspondences in Non-rigid Shapes}, author = {Sipiran, Ivan and Bustos, Benjamin}, booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)}, location = {Sydney, Australia}, pages = {817--824}, numpages = {8}, year = {2013}, month = dec, publisher = {IEEE}, %doi = {}, }
ComputGraph
Data-aware 3D partitioning for generic shape retrieval

Ivan Sipiran, Benjamin Bustos, and Tobias Schreck

Computers & Graphics, Aug 2013

Abs Bib PUBLICATION

In this paper, we present a new approach for generic 3D shape retrieval based on a mesh partitioning scheme. Our method combines a mesh global description and mesh partition descriptions to represent a 3D shape. The partitioning is useful because it helps us to extract additional information in a more local sense. Thus, part descriptions can mitigate the semantic gap imposed by global description methods. We propose to find spatial agglomerations of local features to generate mesh partitions. Hence, the definition of a distance function is stated as an optimization problem to find the best match between two shape representations. We show that mesh partitions are representative and therefore it helps to improve the effectiveness in retrieval tasks. We present exhaustive experimentation using the SHREC’09 Generic Shape Retrieval Benchmark.
@article{sipiran2013dataaware, title = {Data-aware 3D partitioning for generic shape retrieval}, author = {Sipiran, Ivan and Bustos, Benjamin and Schreck, Tobias}, journal = {Computers & Graphics}, %location = {}, volume = {37}, issue = {5}, pages = {460--472}, numpages = {13}, year = {2013}, month = aug, publisher = {Elsevier}, %doi = {10.1016/j.cag.2013.04.002}, }
PatternRecogn
A comparison of methods for non-rigid 3D shape retrieval

Zhouhui Lian, Afzal Godil, Benjamin Bustos, Mohamed Daoudi, Jeroen Hermans, and 14 more authors

Pattern Recognition, Jan 2013

Abs Bib PUBLICATION

Non-rigid 3D shape retrieval has become an active and important research topic in content-based 3D object retrieval. The aim of this paper is to measure and compare the performance of state-of-the-art methods for non-rigid 3D shape retrieval. The paper develops a new benchmark consisting of 600 non-rigid 3D watertight meshes, which are equally classified into 30 categories, to carry out experiments for 11 different algorithms, whose retrieval accuracies are evaluated using six commonly utilized measures.
@article{lian2013comparison, title = {A comparison of methods for non-rigid 3D shape retrieval}, author = {Lian, Zhouhui and Godil, Afzal and Bustos, Benjamin and Daoudi, Mohamed and Hermans, Jeroen and Kawamura, Shun and Kurita, Yukinori and Lavoué, Guillaume and Nguyen, Hien Van and Ohbuchi, Ryutarou and Ohkita, Yuki and Ohishi, Yuki and Porikli, Fatih and Reuter, Martin and Sipiran, Ivan and Smeets, Dirk and Suetens, Paul and Tabia, Hedi and Vandermeulen, Dirk}, journal = {Pattern Recognition}, %location = {}, volume = {46}, issue = {1}, pages = {449--461}, numpages = {13}, year = {2013}, month = jan, publisher = {Elsevier}, %doi = {10.1016/j.patcog.2012.07.014}, }
3DOR
SHREC’13 Track: Large-Scale Partial Shape Retrieval Using Simulated Range Images

Ivan Sipiran, Rodrigo Meruane, Benjamin Bustos, Tobias Schreck, H. Johan, and 2 more authors

In Eurographics Workshop on 3D Object Retrieval (3DOR), May 2013

Abs Bib PUBLICATION

Partial shape retrieval is a challenging problem in content-based 3D model retrieval. This track intends to evaluate the performance of existing algorithms for partial retrieval. The contest is based on a new large-scale query set obtained by mimicking the range image acquisition using a standard 3D benchmark as target set. The query set contains 7200 partial meshes with different levels of complexity. Furthermore, we propose the use of new performance measures based on a partiality factor. With these characteristics, our goal is to evaluate several important aspects: effectiveness, efficiency, robustness and scalability. The obtained results of this track open new questions regarding the difficulty of the partial shape retrieval problem and the scalability of algorithms. In addition, potential future directions on this topic are identified.
@inproceedings{sipiran2013shrec, title = {SHREC'13 Track: Large-Scale Partial Shape Retrieval Using Simulated Range Images}, author = {Sipiran, Ivan and Meruane, Rodrigo and Bustos, Benjamin and Schreck, Tobias and Johan, H. and Li, B. and Lu, Y.}, booktitle = {Eurographics Workshop on 3D Object Retrieval (3DOR)}, %location = {}, pages = {81--88}, numpages = {8}, year = {2013}, month = may, publisher = {Eurographics Association}, %doi = {}, }

2012

3DOR
Key-component detection on 3D meshes using local features

Ivan Sipiran and Benjamin Bustos

In Proc. Eurographics Workshop on 3D Object Retrieval (3DOR’2012), Cagliari, Italy, May 2012

Abs Bib PUBLICATION

In this paper, we present a method to detect stable components on 3D meshes. A component is a region on the mesh which contains discriminative local features. Our goal is to represent a 3D mesh with a set of regions, which we called key-components, that characterize the represented object and therefore, they could be used for effective matching and recognition. As key-components are features in coarse scales, they are less sensitive to mesh deformations such as noise.
@inproceedings{Sipiran2012KeyComponent, title = {Key-component detection on 3D meshes using local features}, author = {Sipiran, Ivan and Bustos, Benjamin}, booktitle = {Proc. Eurographics Workshop on 3D Object Retrieval (3DOR'2012)}, location = {Cagliari, Italy}, pages = {25--32}, year = {2012}, publisher = {Eurographics Association}, %doi = {10.2312/3DOR/3DOR12/025-032}, }

3DOR

SHREC’12 Track: Stability on Abstract Shapes

Silvia Biasotti, Xiang Bai, Benjamin Bustos, Andrea Cerri, Daniela Giorgi, and 5 more authors

In Proc. Eurographics Workshop on 3D Object Retrieval (3DOR’2012), Cagliari, Italy, May 2012

Abs Bib PUBLICATION

@inproceedings{Biasotti2012SHREC12,
  title = {SHREC'12 Track: Stability on Abstract Shapes},
  author = {Biasotti, Silvia and Bai, Xiang and Bustos, Benjamin and Cerri, Andrea and Giorgi, Daniela and Li, Lihua and Mortara, Michela and Sipiran, Ivan and Zhang, Shuqing and Spagnuolo, Michela},
  booktitle = {Proc. Eurographics Workshop on 3D Object Retrieval (3DOR'2012)},
  location = {Cagliari, Italy},
  pages = {33--40},
  year = {2012},
  publisher = {Eurographics Association},
  %doi = {10.2312/3DOR/3DOR12/033-040},
}

3DImaging

3D Shape Matching for Retrieval and Recognition

Benjamin Bustos and Ivan Sipiran

In 3D Imaging, Analysis and Applications, May 2012

Abs Bib PUBLICATION

@incollection{Bustos2012ShapeMatching,
  title = {3D Shape Matching for Retrieval and Recognition},
  author = {Bustos, Benjamin and Sipiran, Ivan},
  booktitle = {3D Imaging, Analysis and Applications},
  editor = {Reinhard, Erik and Dam, Erik and Gooch, Bruce and Shirley, Peter},
  pages = {265--308},
  year = {2012},
  publisher = {Springer London},
  %doi = {10.1007/978-1-4471-4063-4_7},
}

2011

VisComput
Harris 3D: A robust extension of the Harris operator for interest point detection on 3D meshes

Ivan Sipiran and Benjamin Bustos

The Visual Computer, May 2011

Abs Bib PUBLICATION

In this paper, we present an interest points detector for 3D objects based on Harris operator, which has been used with good results in computer vision applications. We propose an adaptive technique to determine the neighborhood of a vertex, over which the Harris response on that vertex is calculated. Our method is robust to several transformations, which can be seen in the high repeatability values obtained using the SHREC feature detection and description benchmark.
@article{Sipiran2011Harris3D, title = {Harris 3D: A robust extension of the Harris operator for interest point detection on 3D meshes}, author = {Sipiran, Ivan and Bustos, Benjamin}, journal = {The Visual Computer}, volume = {27}, number = {11}, pages = {963--976}, year = {2011}, publisher = {Springer}, %doi = {10.1007/s00371-011-0610-y}, }
3DOR
SHREC 2011: Robust Feature Detection and Description Benchmark

Edmond Boyer, Alexander M. Bronstein, Michael M. Bronstein, Benjamin Bustos, Tamar Darom, and 13 more authors

In Proc. Eurographics Workshop on 3D Object Retrieval (3DOR’2011), Llandudno, UK, May 2011

Abs Bib PUBLICATION

Feature-based approaches have recently become very popular in computer vision and image analysis applications, and are becoming a promising direction in shape retrieval. SHREC’11 robust feature detection and description benchmark simulates the feature detection and description stages of feature-based shape retrieval algorithms. The benchmark tests the performance of shape feature detectors and descriptors under a wide variety of transformations.
@inproceedings{Boyer2011SHREC11, title = {SHREC 2011: Robust Feature Detection and Description Benchmark}, author = {Boyer, Edmond and Bronstein, Alexander M. and Bronstein, Michael M. and Bustos, Benjamin and Darom, Tamar and Horaud, Radu and Hotz, Ingrid and Keller, Yaron and Keustermans, Jeroen and Kovnatsky, Artiom and Litman, Ron and Reininghaus, Jan and Sipiran, Ivan and Smeets, Dirk and Suetens, Paul and Vandermeulen, Dirk and Zaharescu, Andrei and Zobel, Volker}, booktitle = {Proc. Eurographics Workshop on 3D Object Retrieval (3DOR'2011)}, location = {Llandudno, UK}, pages = {71--78}, year = {2011}, publisher = {Eurographics Association}, %doi = {10.2312/3DOR/3DOR11/071-078}, }

3DOR

SHREC’11 Track: Shape Retrieval on Non-rigid 3D Watertight Meshes

Zhouhui Lian, Afzal Godil, Benjamin Bustos, Mohamed Daoudi, Jeroen Hermans, and 13 more authors

In Proc. Eurographics Workshop on 3D Object Retrieval (3DOR’2011), Llandudno, UK, May 2011

Abs Bib PUBLICATION

The aim of this track is to measure and compare the performance of non-rigid 3D shape retrieval methods implemented by different participants around the world. The track is based on a new non-rigid 3D shape benchmark, which contains 600 watertight triangle meshes that are equally classified into 30 categories.

@inproceedings{Lian2011SHREC11NonRigid,
  title = {SHREC'11 Track: Shape Retrieval on Non-rigid 3D Watertight Meshes},
  author = {Lian, Zhouhui and Godil, Afzal and Bustos, Benjamin and Daoudi, Mohamed and Hermans, Jeroen and Kawamura, Shun and Kurita, Yuki and Lavoué, Guillaume and Nguyen, Hong-Anh and Ohbuchi, Ryutarou and Ohkita, Yuki and Ohishi, Yusuke and Porikli, Fatih and Reuter, Martin and Sipiran, Ivan and Smeets, Dirk and Suetens, Paul and Vandermeulen, Dirk},
  booktitle = {Proc. Eurographics Workshop on 3D Object Retrieval (3DOR'2011)},
  location = {Llandudno, UK},
  pages = {79--88},
  year = {2011},
  publisher = {Eurographics Association},
  %doi = {10.2312/3DOR/3DOR11/079-088},
}

2010

3DOR
A Robust 3D Interest Points Detector Based on Harris Operator

Ivan Sipiran and Benjamin Bustos

In Proc. Eurographics Workshop on 3D Object Retrieval (3DOR’2010), Norrköping, Sweden, May 2010

Abs Bib PUBLICATION

We propose an adaptive technique to determine the neighborhood of a vertex, over which the Harris response on that vertex is calculated. Our method is robust to several transformations, which can be seen in the high repeatability values obtained using the SHREC feature detection and description benchmark.
@inproceedings{Sipiran2010Harris3D, title = {A Robust 3D Interest Points Detector Based on Harris Operator}, author = {Sipiran, Ivan and Bustos, Benjamin}, booktitle = {Proc. Eurographics Workshop on 3D Object Retrieval (3DOR'2010)}, location = {Norrköping, Sweden}, pages = {7--14}, year = {2010}, publisher = {Eurographics Association}, %doi = {10.2312/3DOR/3DOR10/007-014}, }
3DOR
SHREC 2010: robust feature detection and description benchmark

Alexander M. Bronstein, Michael M. Bronstein, Benjamin Bustos, Umberto Castellani, Marco Crisani, and 9 more authors

In Proc. Eurographics Workshop on 3D Object Retrieval (3DOR’10), Norrköping, Sweden, May 2010

Abs Bib PUBLICATION

Feature-based approaches have recently become very popular in computer vision and image analysis applications, and are becoming a promising direction in shape retrieval. SHREC’10 robust feature detection and description benchmark simulates the feature detection and description stages of feature-based shape retrieval algorithms. The benchmark tests the performance of shape feature detectors and descriptors under a wide variety of transformations. The benchmark allows evaluating how algorithms cope with certain classes of transformations and strength of the transformations that can be dealt with. The present paper is a report of the SHREC’10 robust feature detection and description benchmark results.
@inproceedings{Bronstein2010SHREC, title = {SHREC 2010: robust feature detection and description benchmark}, author = {Bronstein, Alexander M. and Bronstein, Michael M. and Bustos, Benjamin and Castellani, Umberto and Crisani, Marco and Falcidieno, Bianca and Guibas, Leonidas and Kokkinos, Iasonas and Murino, Vittorio and Sipiran, Ivan and Ovsjanikov, Maks and Patane, Giuseppe and Spagnuolo, Michela and Sun, Jian}, booktitle = {Proc. Eurographics Workshop on 3D Object Retrieval (3DOR'10)}, location = {Norrköping, Sweden}, pages = {79--86}, year = {2010}, publisher = {Eurographics Association}, %doi = {10.2312/3DOR/3DOR10/079-086}, }