English
Related papers

Related papers: An intuitive multi-frequency feature representatio…

200 papers

Graph neural networks that model 3D data, such as point clouds or atoms, are typically desired to be $SO(3)$ equivariant, i.e., equivariant to 3D rotations. Unfortunately equivariant convolutions, which are a fundamental operation for…

Machine Learning · Computer Science 2023-06-16 Saro Passaro , C. Lawrence Zitnick

Representation learning has become increasingly important, especially as powerful models have shifted towards learning latent representations before fine-tuning for downstream tasks. This approach is particularly valuable in leveraging the…

Computer Vision and Pattern Recognition · Computer Science 2024-10-17 Shizhe He , Magdalini Paschali , Jiahong Ouyang , Adnan Masood , Akshay Chaudhari , Ehsan Adeli

Convolutional neural networks (CNNs) have massively impacted visual recognition in 2D images, and are now ubiquitous in state-of-the-art approaches. CNNs do not easily extend, however, to data that are not represented by regular grids, such…

Computer Vision and Pattern Recognition · Computer Science 2018-03-29 Nitika Verma , Edmond Boyer , Jakob Verbeek

With the advent of group equivariant convolutions in deep networks literature, spherical CNNs with $\mathsf{SO}(3)$-equivariant layers have been developed to cope with data that are samples of signals on the sphere $S^2$. One can implicitly…

Computer Vision and Pattern Recognition · Computer Science 2023-05-29 Gianfranco Cortes , Yue Yu , Robin Chen , Melissa Armstrong , David Vaillancourt , Baba C. Vemuri

Convolutional Neural Networks (CNNs) have been recently employed to solve problems from both the computer vision and medical image analysis fields. Despite their popularity, most approaches are only able to process 2D images while most…

Computer Vision and Pattern Recognition · Computer Science 2016-06-16 Fausto Milletari , Nassir Navab , Seyed-Ahmad Ahmadi

We demonstrate an object tracking method for 3D images with fixed computational cost and state-of-the-art performance. Previous methods predicted transformation parameters from convolutional layers. We instead propose an architecture that…

Computer Vision and Pattern Recognition · Computer Science 2021-09-28 Daniel Moyer , Esra Abaci Turk , P Ellen Grant , William M. Wells , Polina Golland

We present RangeRCNN, a novel and effective 3D object detection framework based on the range image representation. Most existing methods are voxel-based or point-based. Though several optimizations have been introduced to ease the sparsity…

Computer Vision and Pattern Recognition · Computer Science 2021-03-24 Zhidong Liang , Ming Zhang , Zehan Zhang , Xian Zhao , Shiliang Pu

Existing techniques to encode spatial invariance within deep convolutional neural networks (CNNs) apply the same warping field to all the feature channels. This does not account for the fact that the individual feature channels can…

Computer Vision and Pattern Recognition · Computer Science 2020-07-21 Seungryong Kim , Sabine Süsstrunk , Mathieu Salzmann

This paper proposes a convolution structure for learning SE(3)-equivariant features from 3D point clouds. It can be viewed as an equivariant version of kernel point convolutions (KPConv), a widely used convolution form to process point…

Computer Vision and Pattern Recognition · Computer Science 2023-06-16 Minghan Zhu , Maani Ghaffari , William A. Clark , Huei Peng

In many computer vision tasks, we expect a particular behavior of the output with respect to rotations of the input image. If this relationship is explicitly encoded, instead of treated as any other variation, the complexity of the problem…

Computer Vision and Pattern Recognition · Computer Science 2018-07-06 Diego Marcos , Michele Volpi , Nikos Komodakis , Devis Tuia

3D object detection is receiving increasing attention from both industry and academia thanks to its wide applications in various fields. In this paper, we propose Point-Voxel Region-based Convolution Neural Networks (PV-RCNNs) for 3D object…

Computer Vision and Pattern Recognition · Computer Science 2022-11-09 Shaoshuai Shi , Li Jiang , Jiajun Deng , Zhe Wang , Chaoxu Guo , Jianping Shi , Xiaogang Wang , Hongsheng Li

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

Homogenization is a technique commonly used in multiscale computational science and engineering for predicting collective response of heterogeneous materials and extracting effective mechanical properties. In this paper, a three-dimensional…

Computational Engineering, Finance, and Science · Computer Science 2020-02-19 Chengping Rao , Yang Liu

Deep CNN-based methods have so far achieved the state of the art results in multi-view 3D object reconstruction. Despite the considerable progress, the two core modules of these methods - multi-view feature extraction and fusion, are…

Computer Vision and Pattern Recognition · Computer Science 2021-03-25 Dan Wang , Xinrui Cui , Xun Chen , Zhengxia Zou , Tianyang Shi , Septimiu Salcudean , Z. Jane Wang , Rabab Ward

Automatic 3D neuron reconstruction is critical for analysing the morphology and functionality of neurons in brain circuit activities. However, the performance of existing tracing algorithms is hinged by the low image quality. Recently, a…

Image and Video Processing · Electrical Eng. & Systems 2021-09-17 Heng Wang , Chaoyi Zhang , Jianhui Yu , Yang Song , Siqi Liu , Wojciech Chrzanowski , Weidong Cai

Incorporating inductive bias by embedding geometric entities (such as rays) as input has proven successful in multi-view learning. However, the methods adopting this technique typically lack equivariance, which is crucial for effective 3D…

Computer Vision and Pattern Recognition · Computer Science 2024-11-13 Yinshuang Xu , Dian Chen , Katherine Liu , Sergey Zakharov , Rares Ambrus , Kostas Daniilidis , Vitor Guizilini

We present Point-Voxel CNN (PVCNN) for efficient, fast 3D deep learning. Previous work processes 3D data using either voxel-based or point-based NN models. However, both approaches are computationally inefficient. The computation cost and…

Computer Vision and Pattern Recognition · Computer Science 2019-12-11 Zhijian Liu , Haotian Tang , Yujun Lin , Song Han

Learning about the three-dimensional world from two-dimensional images is a fundamental problem in computer vision. An ideal neural network architecture for such tasks would leverage the fact that objects can be rotated and translated in…

Computer Vision and Pattern Recognition · Computer Science 2023-07-10 Owen Howell , David Klee , Ondrej Biza , Linfeng Zhao , Robin Walters

3D object representation learning is a fundamental challenge in computer vision to infer about the 3D world. Recent advances in deep learning have shown their efficiency in 3D object recognition, among which view-based methods have…

Computer Vision and Pattern Recognition · Computer Science 2021-03-02 Xiang Gao , Wei Hu , Guo-Jun Qi

Deep learning with Convolutional Neural Networks has shown great promise in various areas of image-based classification and enhancement but is often unsuitable for predictive modeling involving non-image based features or features without…

Machine Learning · Computer Science 2020-09-02 Omid Bazgir , Ruibo Zhang , Saugato Rahman Dhruba , Raziur Rahman , Souparno Ghosh , Ranadip Pal