English
Related papers

Related papers: Compositionally Generalizable 3D Structure Predict…

200 papers

Compositional generalization is the ability to generalize systematically to a new data distribution by combining known components. Although humans seem to have a great ability to generalize compositionally, state-of-the-art neural models…

Machine Learning · Computer Science 2021-06-22 Juyong Kim , Pradeep Ravikumar , Joshua Ainslie , Santiago Ontañón

This paper considers the problem of unsupervised 3D object reconstruction from in-the-wild single-view images. Due to ambiguity and intrinsic ill-posedness, this problem is inherently difficult to solve and therefore requires strong…

Machine Learning · Computer Science 2022-07-22 Weiyang Liu , Zhen Liu , Liam Paull , Adrian Weller , Bernhard Schölkopf

Man-made 3D shapes are naturally organized in parts and hierarchies; such structures provide important constraints for shape reconstruction and generation. Modeling shape structures is difficult, because there can be multiple hierarchies…

Computer Vision and Pattern Recognition · Computer Science 2025-04-18 Jiepeng Wang , Hao Pan , Yang Liu , Xin Tong , Taku Komura , Wenping Wang

Humans excel at applying learned behavior to unlearned situations. A crucial component of this generalization behavior is our ability to compose/decompose a whole into reusable parts, an attribute known as compositionality. One of the…

Artificial Intelligence · Computer Science 2024-07-24 Prasanna Vijayaraghavan , Jeffrey Frederic Queisser , Sergio Verduzco Flores , Jun Tani

Key to structured prediction is exploiting the problem structure to simplify the learning process. A major challenge arises when data exhibit a local structure (e.g., are made by "parts") that can be leveraged to better approximate the…

Machine Learning · Statistics 2019-06-03 Carlo Ciliberto , Francis Bach , Alessandro Rudi

Composition-the ability to generate myriad variations from finite means-is believed to underlie powerful generalization. However, compositional generalization remains a key challenge for deep learning. A widely held assumption is that…

Machine Learning · Computer Science 2025-05-27 Qiyao Liang , Daoyuan Qian , Liu Ziyin , Ila Fiete

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

Learning representations that generalize to novel compositions of known concepts is crucial for bridging the gap between human and machine perception. One prominent effort is learning object-centric representations, which are widely…

Machine Learning · Computer Science 2024-11-13 Thaddäus Wiedemer , Jack Brady , Alexander Panfilov , Attila Juhos , Matthias Bethge , Wieland Brendel

We present a novel neural network architecture, termed Decomposer-Composer, for semantic structure-aware 3D shape modeling. Our method utilizes an auto-encoder-based pipeline, and produces a novel factorized shape embedding space, where the…

Computer Vision and Pattern Recognition · Computer Science 2019-10-31 Anastasia Dubrovina , Fei Xia , Panos Achlioptas , Mira Shalah , Raphael Groscot , Leonidas Guibas

Accurately predicting the 3D shape of any arbitrary object in any pose from a single image is a key goal of computer vision research. This is challenging as it requires a model to learn a representation that can infer both the visible and…

Computer Vision and Pattern Recognition · Computer Science 2021-09-03 Anh Thai , Stefan Stojanov , Vijay Upadhya , James M. Rehg

One of the key limitations of modern deep learning approaches lies in the amount of data required to train them. Humans, by contrast, can learn to recognize novel categories from just a few examples. Instrumental to this rapid learning…

Computer Vision and Pattern Recognition · Computer Science 2019-08-20 Pavel Tokmakov , Yu-Xiong Wang , Martial Hebert

Reasoning 3D shapes from 2D images is an essential yet challenging task, especially when only single-view images are at our disposal. While an object can have a complicated shape, individual parts are usually close to geometric primitives…

Computer Vision and Pattern Recognition · Computer Science 2021-07-30 Chun-Han Yao , Wei-Chih Hung , Varun Jampani , Ming-Hsuan Yang

Transfer learning is fundamental for addressing problems in settings with little training data. While several transfer learning approaches have been proposed in 3D, unfortunately, these solutions typically operate on an entire 3D object or…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Souhaib Attaiki , Lei Li , Maks Ovsjanikov

A central goal of visual recognition is to understand objects and scenes from a single image. 2D recognition has witnessed tremendous progress thanks to large-scale learning and general-purpose representations. Comparatively, 3D poses new…

Computer Vision and Pattern Recognition · Computer Science 2023-01-20 Chao-Yuan Wu , Justin Johnson , Jitendra Malik , Christoph Feichtenhofer , Georgia Gkioxari

Reconstructing a complete object from its parts is a fundamental problem in many scientific domains. The purpose of this article is to provide a systematic survey on this topic. The reassembly problem requires understanding the attributes…

Computer Vision and Pattern Recognition · Computer Science 2025-03-28 Jiaxin Lu , Yongqing Liang , Huijun Han , Jiacheng Hua , Junfeng Jiang , Xin Li , Qixing Huang

Monocular 3D shape recovery is fundamental to geometric understanding, yet achieving robust generalization across arbitrary viewpoints and unseen object categories remains a significant challenge. In this paper, we present a generalizable…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Yiyao Ma , Kai Chen , Zhongxiang Zhou , Zhuheng Song , Dongsheng Xie , Zelong Tan , Rong Xiong , Qi Dou

Data-driven generative modeling has made remarkable progress by leveraging the power of deep neural networks. A reoccurring challenge is how to enable a model to generate a rich variety of samples from the entire target distribution, rather…

Graphics · Computer Science 2019-09-04 Nadav Schor , Oren Katzir , Hao Zhang , Daniel Cohen-Or

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

Humans perceive the 3D world as a set of distinct objects that are characterized by various low-level (geometry, reflectance) and high-level (connectivity, adjacency, symmetry) properties. Recent methods based on convolutional neural…

Computer Vision and Pattern Recognition · Computer Science 2020-04-03 Despoina Paschalidou , Luc van Gool , Andreas Geiger

Image captioning models are usually evaluated on their ability to describe a held-out set of images, not on their ability to generalize to unseen concepts. We study the problem of compositional generalization, which measures how well a…

Machine Learning · Computer Science 2019-11-12 Mitja Nikolaus , Mostafa Abdou , Matthew Lamm , Rahul Aralikatte , Desmond Elliott