English
Related papers

Related papers: Denoising-While-Completing Network (DWCNet): Robus…

200 papers

Point clouds captured by depth sensors are often contaminated by noises, obstructing further analysis and applications. In this paper, we emphasize the importance of point distribution uniformity to downstream tasks. We demonstrate that…

Computer Vision and Pattern Recognition · Computer Science 2022-07-22 Tian-Xing Xu , Yuan-Chen Guo , Yong-Liang Yang , Song-Hai Zhang

Point cloud completion aims to recover complete 3D geometry from partial observations caused by limited viewpoints and occlusions. Existing learning-based works, including 3D Convolutional Neural Network (CNN)-based, point-based, and…

Computer Vision and Pattern Recognition · Computer Science 2026-01-28 Jiangyuan Liu , Yuhao Zhao , Hongxuan Ma , Zhe Liu , Jian Wang , Wei Zou

The intricacy of 3D surfaces often results cutting-edge point cloud denoising (PCD) models in surface degradation including remnant noise, wrongly-removed geometric details. Although using multi-scale patches to encode the geometry of a…

Computer Vision and Pattern Recognition · Computer Science 2023-03-22 Anyi Huang , Qian Xie , Zhoutao Wang , Dening Lu , Mingqiang Wei , Jun Wang

Point clouds are often sparse and incomplete. Existing shape completion methods are incapable of generating details of objects or learning the complex point distributions. To this end, we propose a cascaded refinement network together with…

Computer Vision and Pattern Recognition · Computer Science 2020-06-08 Xiaogang Wang , Marcelo H Ang , Gim Hee Lee

Despite recent advancements in deep neural networks for point cloud recognition, real-world safety-critical applications present challenges due to unavoidable data corruption. Current models often fall short in generalizing to unforeseen…

Computer Vision and Pattern Recognition · Computer Science 2023-10-06 Zhuoyuan Wu , Jiachen Sun , Chaowei Xiao

In this paper, we propose an end-to-end deep learning network named 3dDepthNet, which produces an accurate dense depth image from a single pair of sparse LiDAR depth and color image for robotics and autonomous driving tasks. Based on the…

Computer Vision and Pattern Recognition · Computer Science 2020-03-23 Rui Xiang , Feng Zheng , Huapeng Su , Zhe Zhang

Point clouds are a fundamental 3D representation in computer vision, enabling a wide range of perception tasks. However, real-world point clouds often suffer from degradations such as incompleteness, noise, outliers, and irregular density,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Haoqing Wu , Alexa Nawotki , Jochen Garcke

Due to scene complexity, sensor inaccuracies, and processing imprecision, point cloud corruption is inevitable. Over-reliance on input features is the root cause of DNN vulnerabilities. It remains unclear whether this issue exists in 3D…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Zhiqiang Tian , Weigang Li , Chunhua Deng , Junwei Hu , Yongqiang Wang , Wenping Liu

With the rapid advancement of 3D sensing technologies, obtaining 3D shape information of objects has become increasingly convenient. Lidar technology, with its capability to accurately capture the 3D information of objects at long…

Computer Vision and Pattern Recognition · Computer Science 2024-04-25 Weixiao Gao , Ravi Peters , Jantien Stoter

Robust 3D perception under corruption has become an essential task for the realm of 3D vision. While current data augmentation techniques usually perform random transformations on all point cloud objects in an offline way and ignore the…

Computer Vision and Pattern Recognition · Computer Science 2023-09-20 Jie Wang , Lihe Ding , Tingfa Xu , Shaocong Dong , Xinli Xu , Long Bai , Jianan Li

Training deep models for semantic scene completion (SSC) is challenging due to the sparse and incomplete input, a large quantity of objects of diverse scales as well as the inherent label noise for moving objects. To address the…

Computer Vision and Pattern Recognition · Computer Science 2023-03-14 Zhaoyang Xia , Youquan Liu , Xin Li , Xinge Zhu , Yuexin Ma , Yikang Li , Yuenan Hou , Yu Qiao

Noise removal of images is an essential preprocessing procedure for many computer vision tasks. Currently, many denoising models based on deep neural networks can perform well in removing the noise with known distributions (i.e. the…

Computer Vision and Pattern Recognition · Computer Science 2023-06-21 Wencong Wu , Guannan Lv , Yingying Duan , Peng Liang , Yungang Zhang , Yuelong Xia

The task of point cloud completion aims to predict the missing part for an incomplete 3D shape. A widely used strategy is to generate a complete point cloud from the incomplete one. However, the unordered nature of point clouds will degrade…

Computer Vision and Pattern Recognition · Computer Science 2021-06-15 Xin Wen , Peng Xiang , Zhizhong Han , Yan-Pei Cao , Pengfei Wan , Wen Zheng , Yu-Shen Liu

As a dynamic and essential component in the road environment of urban scenarios, vehicles are the most popular investigation targets. To monitor their behavior and extract their geometric characteristics, an accurate and instant measurement…

Computer Vision and Pattern Recognition · Computer Science 2021-02-02 Yan Xia , Yusheng Xu , Cheng Wang , Uwe Stilla

In this paper, we tackle the challenging problem of point cloud completion from the perspective of feature learning. Our key observation is that to recover the underlying structures as well as surface details, given partial input, a…

Computer Vision and Pattern Recognition · Computer Science 2022-09-15 Zejia Su , Haibin Huang , Chongyang Ma , Hui Huang , Ruizhen Hu

How will you repair a physical object with large missings? You may first recover its global yet coarse shape and stepwise increase its local details. We are motivated to imitate the above physical repair procedure to address the point cloud…

Computer Vision and Pattern Recognition · Computer Science 2022-09-07 Fei Hu , Honghua Chen , Xuequan Lu , Zhe Zhu , Jun Wang , Weiming Wang , Fu Lee Wang , Mingqiang Wei

3D scanning is a complex multistage process that generates a point cloud of an object typically containing damaged parts due to occlusions, reflections, shadows, scanner motion, specific properties of the object surface, imperfect…

Computer Vision and Pattern Recognition · Computer Science 2022-01-07 Taras Rumezhak , Oles Dobosevych , Rostyslav Hryniv , Vladyslav Selotkin , Volodymyr Karpiv , Mykola Maksymenko

Point cloud completion is the task of predicting complete geometry from partial observations using a point set representation for a 3D shape. Previous approaches propose neural networks to directly estimate the whole point cloud through…

Computer Vision and Pattern Recognition · Computer Science 2020-10-12 Alexis Mendoza , Alexander Apaza , Ivan Sipiran , Cristian Lopez

Point clouds captured by scanning sensors are often perturbed by noise, which have a highly negative impact on downstream tasks (e.g. surface reconstruction and shape understanding). Previous works mostly focus on training neural networks…

Computer Vision and Pattern Recognition · Computer Science 2025-10-30 Junsheng Zhou , Xingyu Shi , Haichuan Song , Yi Fang , Yu-Shen Liu , Zhizhong Han

Point cloud (PC) processing tasks-such as completion, upsampling, denoising, and colorization-are crucial in applications like autonomous driving and 3D reconstruction. Despite substantial advancements, prior approaches often address each…

Computer Vision and Pattern Recognition · Computer Science 2025-08-22 Yi Du , Zhipeng Zhao , Shaoshu Su , Sharath Golluri , Haoze Zheng , Runmao Yao , Chen Wang