English
Related papers

Related papers: Vector Neurons: A General Framework for SO(3)-Equi…

200 papers

Neural representations have emerged as a new paradigm for applications in rendering, imaging, geometric modeling, and simulation. Compared to traditional representations such as meshes, point clouds, or volumes they can be flexibly…

Computer Vision and Pattern Recognition · Computer Science 2021-05-07 Julien N. P. Martel , David B. Lindell , Connor Z. Lin , Eric R. Chan , Marco Monteiro , Gordon Wetzstein

Deep learning for predicting the electronic-structure Hamiltonian of quantum systems necessitates satisfying the covariance laws, among which achieving SO(3)-equivariance without sacrificing the non-linear expressive capability of networks…

Computational Physics · Physics 2024-06-25 Shi Yin , Xinyang Pan , Xudong Zhu , Tianyu Gao , Haochong Zhang , Feng Wu , Lixin He

6D pose estimation of rigid objects from RGB-D images is crucial for object grasping and manipulation in robotics. Although RGB channels and the depth (D) channel are often complementary, providing respectively the appearance and geometry…

Computer Vision and Pattern Recognition · Computer Science 2022-08-18 Haoran Pan , Jun Zhou , Yuanpeng Liu , Xuequan Lu , Weiming Wang , Xuefeng Yan , Mingqiang Wei

Many applications require the robustness, or ideally the invariance, of a neural network to certain transformations of input data. Most commonly, this requirement is addressed by either augmenting the training data, using adversarial…

Computer Vision and Pattern Recognition · Computer Science 2021-06-21 Kanchana Vaishnavi Gandikota , Jonas Geiping , Zorah Lähner , Adam Czapliński , Michael Moeller

Capsule networks were proposed as an alternative approach to Convolutional Neural Networks (CNNs) for learning object-centric representations, which can be leveraged for improved generalization and sample complexity. Unlike CNNs, capsule…

Computer Vision and Pattern Recognition · Computer Science 2022-06-07 Fabio De Sousa Ribeiro , Kevin Duarte , Miles Everett , Georgios Leontidis , Mubarak Shah

Deep convolutional neural networks (ConvNets) of 3-dimensional kernels allow joint modeling of spatiotemporal features. These networks have improved performance of video and volumetric image analysis, but have been limited in size due to…

Computer Vision and Pattern Recognition · Computer Science 2017-06-13 David Budden , Alexander Matveev , Shibani Santurkar , Shraman Ray Chaudhuri , Nir Shavit

In recent years, neural implicit representations have made remarkable progress in modeling of 3D shapes with arbitrary topology. In this work, we address two key limitations of such representations, in failing to capture local 3D geometric…

Computer Vision and Pattern Recognition · Computer Science 2022-04-01 Yunlu Chen , Basura Fernando , Hakan Bilen , Matthias Nießner , Efstratios Gavves

The ability of convolutional neural networks (CNNs) to recognize objects regardless of their position in the image is due to the translation-equivariance of the convolutional operation. Group-equivariant CNNs transfer this equivariance to…

Computer Vision and Pattern Recognition · Computer Science 2023-04-13 Thomas Wimmer , Vladimir Golkov , Hoai Nam Dang , Moritz Zaiss , Andreas Maier , Daniel Cremers

We describe generalizations of the universal approximation theorem for neural networks to maps invariant or equivariant with respect to linear representations of groups. Our goal is to establish network-like computational models that are…

Neural and Evolutionary Computing · Computer Science 2018-04-30 Dmitry Yarotsky

Convolutional neural networks are state-of-the-art for various segmentation tasks. While for 2D images these networks are also computationally efficient, 3D convolutions have huge storage requirements and therefore, end-to-end training is…

Computer Vision and Pattern Recognition · Computer Science 2022-02-01 Christoph Angermann , Markus Haltmeier

In remote sensing images, the absolute orientation of objects is arbitrary. Depending on an object's orientation and on a sensor's flight path, objects of the same semantic class can be observed in different orientations in the same image.…

Computer Vision and Pattern Recognition · Computer Science 2018-03-19 Diego Marcos , Michele Volpi , Benjamin Kellenberger , Devis Tuia

As $SE(3)$-equivariant graph neural networks mature as a core tool for 3D atomistic modeling, improving their efficiency, expressivity, and physical consistency has become a central challenge for large-scale applications. In this work, we…

Machine Learning · Computer Science 2026-04-13 Yi-Lun Liao , Alexander J. Hoffman , Sabrina C. Shen , Alexandre Duval , Sam Walton Norwood , Tess Smidt

Based on the theory of homogeneous spaces we derive geometrically optimal edge attributes to be used within the flexible message-passing framework. We formalize the notion of weight sharing in convolutional networks as the sharing of…

Machine Learning · Computer Science 2024-03-18 Erik J Bekkers , Sharvaree Vadgama , Rob D Hesselink , Putri A van der Linden , David W Romero

We propose an octree guided neural network architecture and spherical convolutional kernel for machine learning from arbitrary 3D point clouds. The network architecture capitalizes on the sparse nature of irregular point clouds, and…

Computer Vision and Pattern Recognition · Computer Science 2019-03-04 Huan Lei , Naveed Akhtar , Ajmal Mian

By folding into particular 3D structures, proteins play a key role in living beings. To learn meaningful representation from a protein structure for downstream tasks, not only the global backbone topology but the local fine-grained…

Biomolecules · Quantitative Biology 2025-02-05 Jiahan Li , Shitong Luo , Congyue Deng , Chaoran Cheng , Jiaqi Guan , Leonidas Guibas , Jian Peng , Jianzhu Ma

The translation equivariance of convolutional layers enables convolutional neural networks to generalize well on image problems. While translation equivariance provides a powerful inductive bias for images, we often additionally desire…

Machine Learning · Statistics 2020-09-25 Marc Finzi , Samuel Stanton , Pavel Izmailov , Andrew Gordon Wilson

Point cloud is an important type of geometric data structure. Due to its irregular format, most researchers transform such data to regular 3D voxel grids or collections of images. This, however, renders data unnecessarily voluminous and…

Computer Vision and Pattern Recognition · Computer Science 2017-04-12 Charles R. Qi , Hao Su , Kaichun Mo , Leonidas J. Guibas

Learning functions on point clouds has applications in many fields, including computer vision, computer graphics, physics, and chemistry. Recently, there has been a growing interest in neural architectures that are invariant or equivariant…

Machine Learning · Computer Science 2020-10-07 Nadav Dym , Haggai Maron

In this work we investigate how to achieve equivariance to input transformations in deep networks, purely from data, without being given a model of those transformations. Convolutional Neural Networks (CNNs), for example, are equivariant to…

Computer Vision and Pattern Recognition · Computer Science 2021-11-29 Jianbo Jiao , João F. Henriques

Many scientific and geometric problems exhibit general linear symmetries, yet most equivariant neural networks are built for compact groups or simple vector features, limiting their reuse on matrix-valued data such as covariances, inertias,…

Machine Learning · Computer Science 2026-02-02 Chankyo Kim , Sicheng Zhao , Minghan Zhu , Tzu-Yuan Lin , Maani Ghaffari
‹ Prev 1 4 5 6 7 8 10 Next ›