English
Related papers

Related papers: ShapeMatcher: Self-Supervised Joint Shape Canonica…

200 papers

We address the problem of discovering part segmentations of articulated objects without supervision. In contrast to keypoints, part segmentations provide information about part localizations on the level of individual pixels. Capturing both…

Computer Vision and Pattern Recognition · Computer Science 2020-09-11 Sandro Braun , Patrick Esser , Björn Ommer

Canonicalization is a widely used strategy in equivariant machine learning, enforcing symmetry in neural networks by mapping each input to a standard form. Yet, it often introduces discontinuities that can affect stability during training,…

Machine Learning · Computer Science 2026-04-17 Ya-Wei Eileen Lin , Ron Levie

This paper provides a novel framework that learns canonical embeddings for non-rigid shape matching. In contrast to prior work in this direction, our framework is trained end-to-end and thus avoids instabilities and constraints associated…

Computer Vision and Pattern Recognition · Computer Science 2021-10-08 Abhishek Sharma , Maks Ovsjanikov

Learning embeddings that are invariant to the pose of the object is crucial in visual image retrieval and re-identification. The existing approaches for person, vehicle, or animal re-identification tasks suffer from high intra-class…

Computer Vision and Pattern Recognition · Computer Science 2020-08-27 Olga Moskvyak , Frederic Maire , Feras Dayoub , Mahsa Baktashmotlagh

In the domain of single-view 3D reconstruction, traditional techniques have frequently relied on expensive and time-intensive 3D annotation data. Facing the challenge of annotation acquisition, semi-supervised learning strategies offer an…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Wei Zhoua , Xinzhe Shia , Yunfeng Shea , Kunlong Liua , Yongqin Zhanga

Large intra-class variation is the result of changes in multiple object characteristics. Images, however, only show the superposition of different variable factors such as appearance or shape. Therefore, learning to disentangle and…

Computer Vision and Pattern Recognition · Computer Science 2019-06-18 Dominik Lorenz , Leonard Bereska , Timo Milbich , Björn Ommer

We present a new approach to 3D object representation where a neural network encodes the geometry of an object directly into the weights and biases of a second 'mapping' network. This mapping network can be used to reconstruct an object by…

Machine Learning · Computer Science 2020-04-07 Eric Mitchell , Selim Engin , Volkan Isler , Daniel D Lee

Spatially localized deformation components are very useful for shape analysis and synthesis in 3D geometry processing. Several methods have recently been developed, with an aim to extract intuitive and interpretable deformation components.…

Graphics · Computer Science 2017-12-19 Qingyang Tan , Lin Gao , Yu-Kun Lai , Jie Yang , Shihong Xia

Category-level object pose estimation aims to determine the pose and size of novel objects in specific categories. Existing correspondence-based approaches typically adopt point-based representations to establish the correspondences between…

Computer Vision and Pattern Recognition · Computer Science 2025-03-20 Huan Ren , Wenfei Yang , Xiang Liu , Shifeng Zhang , Tianzhu Zhang

Recently customized generation has significant potential, which uses as few as 3-5 user-provided images to train a model to synthesize new images of a specified subject. Though subsequent applications enhance the flexibility and diversity…

Computer Vision and Pattern Recognition · Computer Science 2024-07-15 Tianchu Guo , Pengyu Li , Biao Wang , Xiansheng Hua

Articulated objects exist widely in the real world. However, previous 3D generative methods for unsupervised part decomposition are unsuitable for such objects, because they assume a spatially fixed part location, resulting in inconsistent…

Computer Vision and Pattern Recognition · Computer Science 2021-10-12 Yuki Kawana , Yusuke Mukuta , Tatsuya Harada

Object pose refinement is essential for robust object pose estimation. Previous work has made significant progress towards instance-level object pose refinement. Yet, category-level pose refinement is a more challenging problem due to large…

Computer Vision and Pattern Recognition · Computer Science 2024-04-18 Linfang Zheng , Tze Ho Elden Tse , Chen Wang , Yinghan Sun , Hua Chen , Ales Leonardis , Wei Zhang

The impressive performance of deep convolutional neural networks in single-view 3D reconstruction suggests that these models perform non-trivial reasoning about the 3D structure of the output space. Recent work has challenged this belief,…

Computer Vision and Pattern Recognition · Computer Science 2021-06-17 Mateusz Michalkiewicz , Stavros Tsogkas , Sarah Parisot , Mahsa Baktashmotlagh , Anders Eriksson , Eugene Belilovsky

3D morphable models (3DMMs) are a powerful tool to represent the possible shapes and appearances of an object category. Given a single test image, 3DMMs can be used to solve various tasks, such as predicting the 3D shape, pose, semantic…

Computer Vision and Pattern Recognition · Computer Science 2025-05-01 Leonhard Sommer , Olaf Dünkel , Christian Theobalt , Adam Kortylewski

Human shape spaces have been extensively studied, as they are a core element of human shape and pose inference tasks. Classic methods for creating a human shape model register a surface template mesh to a database of 3D scans and use…

Computer Vision and Pattern Recognition · Computer Science 2024-06-24 Stephan Wenninger , Fabian Kemper , Ulrich Schwanecke , Mario Botsch

Image segmentation is about grouping pixels with different semantics, e.g., category or instance membership, where each choice of semantics defines a task. While only the semantics of each task differ, current research focuses on designing…

Computer Vision and Pattern Recognition · Computer Science 2022-06-17 Bowen Cheng , Ishan Misra , Alexander G. Schwing , Alexander Kirillov , Rohit Girdhar

Aiming at inferring 3D shapes from 2D images, 3D shape reconstruction has drawn huge attention from researchers in computer vision and deep learning communities. However, it is not practical to assume that 2D input images and their…

Computer Vision and Pattern Recognition · Computer Science 2018-11-30 Yi-Lun Liao , Yao-Cheng Yang , Yu-Chiang Frank Wang

Articulated objects are pervasive in daily life. However, due to the intrinsic high-DoF structure, the joint states of the articulated objects are hard to be estimated. To model articulated objects, two kinds of shape deformations namely…

Computer Vision and Pattern Recognition · Computer Science 2021-12-15 Han Xue , Liu Liu , Wenqiang Xu , Haoyuan Fu , Cewu Lu

We address the task of estimating camera parameters from a set of images depicting a scene. Popular feature-based structure-from-motion (SfM) tools solve this task by incremental reconstruction: they repeat triangulation of sparse 3D points…

Computer Vision and Pattern Recognition · Computer Science 2024-07-29 Eric Brachmann , Jamie Wynn , Shuai Chen , Tommaso Cavallari , Áron Monszpart , Daniyar Turmukhambetov , Victor Adrian Prisacariu

Dense geometric matching determines the dense pixel-wise correspondence between a source and support image corresponding to the same 3D structure. Prior works employ an encoder of transformer blocks to correlate the two-frame features.…

Computer Vision and Pattern Recognition · Computer Science 2023-03-31 Shengjie Zhu , Xiaoming Liu