English
Related papers

Related papers: Effective Rotation-invariant Point CNN with Spheri…

200 papers

A desireable property of accelerometric gait-based identification systems is robustness to new device orientations presented by users during testing but unseen during the training phase. However, traditional Convolutional neural networks…

Computer Vision and Pattern Recognition · Computer Science 2020-08-18 Bowen Jing , Vinay Prabhu , Angela Gu , John Whaley

Deep neural networks have achieved great success in the last decade. When designing neural networks to handle the ubiquitous geometric data such as point clouds and graphs, it is critical that the model can maintain invariance towards…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Ziwei Zhang , Xin Wang , Zeyang Zhang , Peng Cui , Wenwu Zhu

We present a new permutation-invariant network for 3D point cloud processing. Our network is composed of a recurrent set encoder and a convolutional feature aggregator. Given an unordered point set, the encoder firstly partitions its…

Computer Vision and Pattern Recognition · Computer Science 2019-11-26 Pengxiang Wu , Chao Chen , Jingru Yi , Dimitris Metaxas

The intrinsic rotation invariance lies at the core of matching point clouds with handcrafted descriptors. However, it is widely despised by recent deep matchers that obtain the rotation invariance extrinsically via data augmentation. As the…

Computer Vision and Pattern Recognition · Computer Science 2024-03-28 Hao Yu , Zheng Qin , Ji Hou , Mahdi Saleh , Dongsheng Li , Benjamin Busam , Slobodan Ilic

In recent years, Convolutional Neural Networks (CNN) have proven to be efficient analysis tools for processing point clouds, e.g., for reconstruction, segmentation and classification. In this paper, we focus on the classification of edges…

Rotation invariance has been studied in the computer vision community primarily in the context of small in-plane rotations. This is usually achieved by building invariant image features. However, the problem of achieving invariance for…

Computer Vision and Pattern Recognition · Computer Science 2016-11-18 Lokesh Boominathan , Suraj Srinivas , R. Venkatesh Babu

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 this paper, we propose PCPNet, a deep-learning based approach for estimating local 3D shape properties in point clouds. In contrast to the majority of prior techniques that concentrate on global or mid-level attributes, e.g., for shape…

Computational Geometry · Computer Science 2018-06-20 Paul Guerrero , Yanir Kleiman , Maks Ovsjanikov , Niloy J. Mitra

Point-cloud is an efficient way to represent 3D world. Analysis of point-cloud deals with understanding the underlying 3D geometric structure. But due to the lack of smooth topology, and hence the lack of neighborhood structure, standard…

Computer Vision and Pattern Recognition · Computer Science 2019-10-31 Liu Yang , Rudrasis Chakraborty , Stella X. Yu

Learning 3D representations that generalize well to arbitrarily oriented inputs is a challenge of practical importance in applications varying from computer vision to physics and chemistry. We propose a novel multi-resolution convolutional…

Machine Learning · Computer Science 2021-03-22 James Fox , Bo Zhao , Sivasankaran Rajamanickam , Rampi Ramprasad , Le Song

We present S2P-Net (Spectral-Spatial Polar Network), a compact deep learning architecture that achieves mathematically guaranteed rotation invariance without data augmentation. In this Paper, we also made a comparison to other neural…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Albert Heruth

State-of-the-art deep learning systems often require large amounts of data and computation. For this reason, leveraging known or unknown structure of the data is paramount. Convolutional neural networks (CNNs) are successful examples of…

Computer Vision and Pattern Recognition · Computer Science 2020-12-07 Carlos Esteves

Establishing correspondence between shapes is a fundamental problem in geometry processing, arising in a wide variety of applications. The problem is especially difficult in the setting of non-isometric deformations, as well as in the…

Computer Vision and Pattern Recognition · Computer Science 2016-05-23 Davide Boscaini , Jonathan Masci , Emanuele Rodolà , Michael M. Bronstein

Omnidirectional images and spherical representations of $3D$ shapes cannot be processed with conventional 2D convolutional neural networks (CNNs) as the unwrapping leads to large distortion. Using fast implementations of spherical and…

Computer Vision and Pattern Recognition · Computer Science 2020-12-09 Suhas Lohit , Shubhendu Trivedi

Convolutional Neural Networks (CNNs) are extremely efficient, since they exploit the inherent translation-invariance of natural images. However, translation is just one of a myriad of useful spatial transformations. Can the same efficiency…

Computer Vision and Pattern Recognition · Computer Science 2021-12-02 João F. Henriques , Andrea Vedaldi

Neural networks (NNs) have been shown to be competitive against state-of-the-art feature engineering and random forest (RF) classification of periodic variable stars. Although previous work utilising NNs has made use of periodicity by…

Instrumentation and Methods for Astrophysics · Physics 2021-05-12 Keming Zhang , Joshua S. Bloom

The success of convolutional networks in learning problems involving planar signals such as images is due to their ability to exploit the translation symmetry of the data distribution through weight sharing. Many areas of science and…

Machine Learning · Computer Science 2019-04-23 Taco Cohen , Mario Geiger , Jonas Köhler , Max Welling

We present Kernel Point Convolution (KPConv), a new design of point convolution, i.e. that operates on point clouds without any intermediate representation. The convolution weights of KPConv are located in Euclidean space by kernel points,…

Computer Vision and Pattern Recognition · Computer Science 2019-08-20 Hugues Thomas , Charles R. Qi , Jean-Emmanuel Deschaud , Beatriz Marcotegui , François Goulette , Leonidas J. Guibas

The convolutional neural network (CNN) is one of the most commonly used architectures for computer vision tasks. The key building block of a CNN is the convolutional kernel that aggregates information from the pixel neighborhood and shares…

Image and Video Processing · Electrical Eng. & Systems 2022-02-08 Tianyu Ma , Alan Q. Wang , Adrian V. Dalca , Mert R. Sabuncu

We address the problem of 3D rotation equivariance in convolutional neural networks. 3D rotations have been a challenging nuisance in 3D classification tasks requiring higher capacity and extended data augmentation in order to tackle it. We…

Computer Vision and Pattern Recognition · Computer Science 2018-10-01 Carlos Esteves , Christine Allen-Blanchette , Ameesh Makadia , Kostas Daniilidis
‹ Prev 1 3 4 5 6 7 10 Next ›