English
Related papers

Related papers: Point Cloud Processing via Recurrent Set Encoding

200 papers

This paper proposes a set of rules to revise various neural networks for 3D point cloud processing to rotation-equivariant quaternion neural networks (REQNNs). We find that when a neural network uses quaternion features under certain…

Computer Vision and Pattern Recognition · Computer Science 2020-10-13 Wen Shen , Binbin Zhang , Shikun Huang , Zhihua Wei , Quanshi Zhang

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

We propose an approach to instance segmentation from 3D point clouds based on dynamic convolution. This enables it to adapt, at inference, to varying feature and object scales. Doing so avoids some pitfalls of bottom up approaches,…

Computer Vision and Pattern Recognition · Computer Science 2022-10-17 Tong He , Chunhua Shen , Anton van den Hengel

Due to limitations in acquisition equipment, noise perturbations often corrupt 3-D point clouds, hindering down-stream tasks such as surface reconstruction, rendering, and further processing. Existing 3-D point cloud denoising methods…

Computer Vision and Pattern Recognition · Computer Science 2024-11-22 Wenqiang Xu , Wenrui Dai , Duoduo Xue , Ziyang Zheng , Chenglin Li , Junni Zou , Hongkai Xiong

We study the problem of efficient semantic segmentation of large-scale 3D point clouds. By relying on expensive sampling techniques or computationally heavy pre/post-processing steps, most existing approaches are only able to be trained and…

Computer Vision and Pattern Recognition · Computer Science 2021-07-07 Qingyong Hu , Bo Yang , Linhai Xie , Stefano Rosa , Yulan Guo , Zhihua Wang , Niki Trigoni , Andrew Markham

Deep neural networks require specific layers to process point clouds, as the scattered and irregular location of 3D points prevents the use of conventional convolutional filters. We introduce the composite layer, a flexible and general…

Computer Vision and Pattern Recognition · Computer Science 2024-10-16 Alberto Floris , Luca Frittoli , Diego Carrera , Giacomo Boracchi

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

In this paper, we propose a deep hierarchical attention context model for lossless attribute compression of point clouds, leveraging a multi-resolution spatial structure and residual learning. A simple and effective Level of Detail (LoD)…

Computer Vision and Pattern Recognition · Computer Science 2025-04-02 Yueru Chen , Wei Zhang , Dingquan Li , Jing Wang , Ge Li

Point clouds are an efficient data format for 3D data. However, existing 3D segmentation methods for point clouds either do not model local dependencies \cite{pointnet} or require added computations \cite{kd-net,pointnet2}. This work…

Computer Vision and Pattern Recognition · Computer Science 2018-04-02 Qiangui Huang , Weiyue Wang , Ulrich Neumann

Feature learning on point clouds has shown great promise, with the introduction of effective and generalizable deep learning frameworks such as pointnet++. Thus far, however, point features have been abstracted in an independent and…

Computer Vision and Pattern Recognition · Computer Science 2018-03-16 Chu Wang , Babak Samari , Kaleem Siddiqi

While 3D point clouds are widely used in vision applications, their irregular and sparse nature make them challenging to handle. In response, numerous encoding approaches have been proposed to capture the rich semantic information of point…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Donghyun Kim , Chanyoung Kim , Hyunah Ko , Seong Jae Hwang

Extending the translation equivariance property of convolutional neural networks to larger symmetry groups has been shown to reduce sample complexity and enable more discriminative feature learning. Further, exploiting additional symmetries…

Computer Vision and Pattern Recognition · Computer Science 2025-02-12 Lisa Weijler , Pedro Hermosilla

With the development of 3D sensing technologies, point clouds have attracted increasing attention in a variety of applications for 3D object representation, such as autonomous driving, 3D immersive tele-presence and heritage reconstruction.…

Computer Vision and Pattern Recognition · Computer Science 2019-01-01 Junkun Qi , Wei Hu , Zongming Guo

Neural Machine Translation model is a sequence-to-sequence converter based on neural networks. Existing models use recurrent neural networks to construct both the encoder and decoder modules. In alternative research, the recurrent networks…

Computation and Language · Computer Science 2021-05-04 Ritam Mallick , Seba Susan , Vaibhaw Agrawal , Rizul Garg , Prateek Rawal

Previous top-performing approaches for point cloud instance segmentation involve a bottom-up strategy, which often includes inefficient operations or complex pipelines, such as grouping over-segmented components, introducing additional…

Computer Vision and Pattern Recognition · Computer Science 2021-03-09 Tong He , Chunhua Shen , Anton van den Hengel

Convolutional networks are the de-facto standard for analyzing spatio-temporal data such as images, videos, and 3D shapes. Whilst some of this data is naturally dense (e.g., photos), many other data sources are inherently sparse. Examples…

Computer Vision and Pattern Recognition · Computer Science 2017-11-29 Benjamin Graham , Martin Engelcke , Laurens van der Maaten

Point clouds obtained from 3D scans are typically sparse, irregular, and noisy, and required to be consolidated. In this paper, we present the first deep learning based edge-aware technique to facilitate the consolidation of point clouds.…

Computer Vision and Pattern Recognition · Computer Science 2018-07-18 Lequan Yu , Xianzhi Li , Chi-Wing Fu , Daniel Cohen-Or , Pheng-Ann Heng

Modeling object dynamics with a neural network is an important problem with numerous applications. Most recent work has been based on graph neural networks. However, physics happens in 3D space, where geometric information potentially plays…

Computer Vision and Pattern Recognition · Computer Science 2024-04-10 Chanho Kim , Li Fuxin

3D point clouds are rich in geometric structure information, while 2D images contain important and continuous texture information. Combining 2D information to achieve better 3D semantic segmentation has become mainstream in 3D scene…

Computer Vision and Pattern Recognition · Computer Science 2022-12-14 Chaolong Yang , Yuyao Yan , Weiguang Zhao , Jianan Ye , Xi Yang , Amir Hussain , Kaizhu Huang

Deep neural networks have enjoyed remarkable success for various vision tasks, however it remains challenging to apply CNNs to domains lacking a regular underlying structures such as 3D point clouds. Towards this we propose a novel…

Computer Vision and Pattern Recognition · Computer Science 2018-09-13 Yifan Xu , Tianqi Fan , Mingye Xu , Long Zeng , Yu Qiao