English
Related papers

Related papers: Rotation Invariant Convolutions for 3D Point Cloud…

200 papers

This paper analyzes the robustness of recent 3D shape descriptors to SO(3) rotations, something that is fundamental to shape modeling. Specifically, we formulate the task of rotated 3D object instance detection. To do so, we consider a…

Computer Vision and Pattern Recognition · Computer Science 2023-05-31 Supriya Gadi Patil , Angel X. Chang , Manolis Savva

We introduce PointConvFormer, a novel building block for point cloud based deep network architectures. Inspired by generalization theory, PointConvFormer combines ideas from point convolution, where filter weights are only based on relative…

Computer Vision and Pattern Recognition · Computer Science 2023-05-12 Wenxuan Wu , Li Fuxin , Qi Shan

Learning generative models of 3D point clouds is one of the fundamental problems in 3D generative learning. One of the key properties of point clouds is their permutation invariance, i.e., changing the order of points in a point cloud does…

Computer Vision and Pattern Recognition · Computer Science 2025-02-19 Ka-Hei Hui , Chao Liu , Xiaohui Zeng , Chi-Wing Fu , Arash Vahdat

The introduction of cheap RGB-D cameras, stereo cameras, and LIDAR devices has given the computer vision community 3D information that conventional RGB cameras cannot provide. This data is often stored as a point cloud. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2018-10-22 Aleksandr Savchenkov , Andrew Davis , Xuan Zhao

With the rise of large-scale models trained on broad data, in-context learning has become a new learning paradigm that has demonstrated significant potential in natural language processing and computer vision tasks. Meanwhile, in-context…

Computer Vision and Pattern Recognition · Computer Science 2023-12-29 Zhongbin Fang , Xiangtai Li , Xia Li , Joachim M. Buhmann , Chen Change Loy , Mengyuan Liu

Many recent works show that a spatial manipulation module could boost the performances of deep neural networks (DNNs) for 3D point cloud analysis. In this paper, we aim to provide an insight into spatial manipulation modules. Firstly, we…

Computer Vision and Pattern Recognition · Computer Science 2021-07-08 Shuang Deng , Bo Liu , Qiulei Dong , Zhanyi Hu

We present a novel deep learning framework for flow field predictions in irregular domains when the solution is a function of the geometry of either the domain or objects inside the domain. Grid vertices in a computational fluid dynamics…

Machine Learning · Computer Science 2021-09-20 Ali Kashefi , Davis Rempe , Leonidas J. Guibas

Deep convolutional neural networks accuracy is heavily impacted by rotations of the input data. In this paper, we propose a convolutional predictor that is invariant to rotations in the input. This architecture is capable of predicting the…

Computer Vision and Pattern Recognition · Computer Science 2021-05-24 Rosemberg Rodriguez Salas , Eva Dokladalova , Petr Dokládal

Point clouds are often the default choice for many applications as they exhibit more flexibility and efficiency than volumetric data. Nevertheless, their unorganized nature -- points are stored in an unordered way -- makes them less suited…

Computer Vision and Pattern Recognition · Computer Science 2020-08-18 Yida Wang , David Joseph Tan , Nassir Navab , Federico Tombari

We present a 3D capsule module for processing point clouds that is equivariant to 3D rotations and translations, as well as invariant to permutations of the input points. The operator receives a sparse set of local reference frames,…

Machine Learning · Computer Science 2020-08-25 Yongheng Zhao , Tolga Birdal , Jan Eric Lenssen , Emanuele Menegatti , Leonidas Guibas , Federico Tombari

Convolution has been the core ingredient of modern neural networks, triggering the surge of deep learning in vision. In this work, we rethink the inherent principles of standard convolution for vision tasks, specifically spatial-agnostic…

Computer Vision and Pattern Recognition · Computer Science 2021-04-13 Duo Li , Jie Hu , Changhu Wang , Xiangtai Li , Qi She , Lei Zhu , Tong Zhang , Qifeng Chen

We present an approach to semantic scene analysis using deep convolutional networks. Our approach is based on tangent convolutions - a new construction for convolutional networks on 3D data. In contrast to volumetric approaches, our method…

Computer Vision and Pattern Recognition · Computer Science 2018-07-09 Maxim Tatarchenko , Jaesik Park , Vladlen Koltun , Qian-Yi Zhou

Rotation invariance and translation invariance have great values in image recognition tasks. In this paper, we bring a new architecture in convolutional neural network (CNN) named cyclic convolutional layer to achieve rotation invariance in…

Computer Vision and Pattern Recognition · Computer Science 2017-06-20 Shiyuan Li

Feature descriptors of point clouds are used in several applications, such as registration and part segmentation of 3D point clouds. Learning discriminative representations of local geometric features is unquestionably the most important…

Computer Vision and Pattern Recognition · Computer Science 2022-09-01 Seunghwan Jung , Yeong-Gil Shin , Minyoung Chung

Point cloud completion is a generation and estimation issue derived from the partial point clouds, which plays a vital role in the applications in 3D computer vision. The progress of deep learning (DL) has impressively improved the…

Computer Vision and Pattern Recognition · Computer Science 2023-01-02 Ben Fei , Weidong Yang , Wenming Chen , Zhijun Li , Yikang Li , Tao Ma , Xing Hu , Lipeng Ma

Despite the remarkable success of deep learning, an optimal convolution operation on point clouds remains elusive owing to their irregular data structure. Existing methods mainly focus on designing an effective continuous kernel function…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Sungmin Woo , Dogyoon Lee , Sangwon Hwang , Woojin Kim , Sangyoun Lee

We introduce FPConv, a novel surface-style convolution operator designed for 3D point cloud analysis. Unlike previous methods, FPConv doesn't require transforming to intermediate representation like 3D grid or graph and directly works on…

Computer Vision and Pattern Recognition · Computer Science 2020-03-17 Yiqun Lin , Zizheng Yan , Haibin Huang , Dong Du , Ligang Liu , Shuguang Cui , Xiaoguang Han

Convolutional neural networks have shown great success on feature extraction from raw input data such as images. Although convolutional neural networks are invariant to translations on the inputs, they are not invariant to other…

Computer Vision and Pattern Recognition · Computer Science 2018-09-05 Hongyang Gao , Shuiwang Ji

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

Convolution on 3D point clouds is widely researched yet far from perfect in geometric deep learning. The traditional wisdom of convolution characterises feature correspondences indistinguishably among 3D points, arising an intrinsic…

Computer Vision and Pattern Recognition · Computer Science 2023-01-11 Mingqiang Wei , Zeyong Wei , Haoran Zhou , Fei Hu , Huajian Si , Zhilei Chen , Zhe Zhu , Jingbo Qiu , Xuefeng Yan , Yanwen Guo , Jun Wang , Jing Qin