English
Related papers

Related papers: KPConv: Flexible and Deformable Convolution for Po…

200 papers

Unlike on images, semantic learning on 3D point clouds using a deep network is challenging due to the naturally unordered data structure. Among existing works, PointNet has achieved promising results by directly learning on point sets.…

Computer Vision and Pattern Recognition · Computer Science 2018-04-05 Yiru Shen , Chen Feng , Yaoqing Yang , Dong Tian

This work proposes a general-purpose, fully-convolutional network architecture for efficiently processing large-scale 3D data. One striking characteristic of our approach is its ability to process unorganized 3D representations such as…

Computer Vision and Pattern Recognition · Computer Science 2018-08-22 Dario Rethage , Johanna Wald , Jürgen Sturm , Nassir Navab , Federico Tombari

Model compression and acceleration are attracting increasing attentions due to the demand for embedded devices and mobile applications. Research on efficient convolutional neural networks (CNNs) aims at removing feature redundancy by…

Machine Learning · Computer Science 2020-08-21 Jinhua Liang , Tao Zhang , Guoqing Feng

Point clouds are unstructured and unordered in the embedded 3D space. In order to produce consistent responses under different permutation layouts, most existing methods aggregate local spatial points through maximum or summation operation.…

Computer Vision and Pattern Recognition · Computer Science 2020-09-04 Yuan Fang , Chunyan Xu , Zhen Cui , Yuan Zong , Jian Yang

Transformers have revolutionized the point cloud learning task, but the quadratic complexity hinders its extension to long sequence and makes a burden on limited computational resources. The recent advent of RWKV, a fresh breed of deep…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Qingdong He , Jiangning Zhang , Jinlong Peng , Haoyang He , Xiangtai Li , Yabiao Wang , Chengjie Wang

In point cloud compression, the quality of a reconstructed point cloud relies on both the global structure and the local context, with existing methods usually processing global and local information sequentially and lacking communication…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Xuan Deng , Xingtao Wang , Xiandong Meng , Xiaopeng Fan , Debin Zhao

We present a new versatile building block for deep point cloud processing architectures that is equally suited for diverse tasks. This building block combines the ideas of spatial transformers and multi-view convolutional networks with the…

Computer Vision and Pattern Recognition · Computer Science 2021-10-05 Kirill Mazur , Victor Lempitsky

Deep Neural Networks, particularly Convolutional Neural Networks (ConvNets), have achieved incredible success in many vision tasks, but they usually require millions of parameters for good accuracy performance. With increasing applications…

Computer Vision and Pattern Recognition · Computer Science 2022-03-30 Yuhuang Hu , Shih-Chii Liu

Multi-Layer Perceptrons (MLPs) have become one of the fundamental architectural component in point cloud analysis due to its effective feature learning mechanism. However, when processing complex geometric structures in point clouds, MLPs'…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Yan Shi , Qingdong He , Yijun Liu , Xiaoyu Liu , Jingyong Su

Despite the recent development of deep learning-based point cloud upsampling, most MLP-based point cloud upsampling methods have limitations in that it is difficult to train the local and global structure of the point cloud at the same…

Computer Vision and Pattern Recognition · Computer Science 2023-05-03 Dohoon Kim , Minwoo Shin , Joonki Paik

Point clouds are a very efficient way to represent volumetric data in medical imaging. First, they do not occupy resources for empty spaces and therefore can avoid trade-offs between resolution and field-of-view for voxel-based 3D…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Mattias Paul Heinrich

To better address challenging issues of the irregularity and inhomogeneity inherently present in 3D point clouds, researchers have been shifting their focus from the design of hand-craft point feature towards the learning of 3D point…

Computer Vision and Pattern Recognition · Computer Science 2022-11-21 Xiang Li , Mingyang Wang , Congcong Wen , Lingjing Wang , Nan Zhou , Yi Fang

Architectures that first convert point clouds to a grid representation and then apply convolutional neural networks achieve good performance for radar-based object detection. However, the transfer from irregular point cloud data to a dense…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Daniel Köhler , Maurice Quach , Michael Ulrich , Frank Meinl , Bastian Bischoff , Holger Blume

When designing Convolutional Neural Networks (CNNs), one must select the size\break of the convolutional kernels before training. Recent works show CNNs benefit from different kernel sizes at different layers, but exploring all possible…

Computer Vision and Pattern Recognition · Computer Science 2022-03-18 David W. Romero , Robert-Jan Bruintjes , Jakub M. Tomczak , Erik J. Bekkers , Mark Hoogendoorn , Jan C. van Gemert

We present CpT: Convolutional point Transformer - a novel deep learning architecture for dealing with the unstructured nature of 3D point cloud data. CpT is an improvement over existing attention-based Convolutions Neural Networks as well…

Computer Vision and Pattern Recognition · Computer Science 2021-11-23 Chaitanya Kaul , Joshua Mitton , Hang Dai , Roderick Murray-Smith

Convolutional neural networks (CNNs) have enabled the state-of-the-art performance in many computer vision tasks. However, little effort has been devoted to establishing convolution in non-linear space. Existing works mainly leverage on the…

Computer Vision and Pattern Recognition · Computer Science 2020-05-25 Chen Wang , Jianfei Yang , Lihua Xie , Junsong Yuan

Depthwise separable convolutions and frequency-domain convolutions are two recent ideas for building efficient convolutional neural networks. They are seemingly incompatible: the vast majority of operations in depthwise separable CNNs are…

Computer Vision and Pattern Recognition · Computer Science 2021-09-17 Mark Buckler , Neil Adit , Yuwei Hu , Zhiru Zhang , Adrian Sampson

Conventional neural architectures for sequential data present important limitations. Recurrent networks suffer from exploding and vanishing gradients, small effective memory horizons, and must be trained sequentially. Convolutional networks…

Machine Learning · Computer Science 2022-03-18 David W. Romero , Anna Kuzina , Erik J. Bekkers , Jakub M. Tomczak , Mark Hoogendoorn

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

We present a novel rotation invariant architecture operating directly on point cloud data. We demonstrate how rotation invariance can be injected into a recently proposed point-based PCNN architecture, at all layers of the network,…

Computer Vision and Pattern Recognition · Computer Science 2021-05-07 Adrien Poulenard , Marie-Julie Rakotosaona , Yann Ponty , Maks Ovsjanikov