English
Related papers

Related papers: Learning Spatial and Temporal Variations for 4D Po…

200 papers

Exploiting past 3D LiDAR scans to predict future point clouds is a promising method for autonomous mobile systems to realize foresighted state estimation, collision avoidance, and planning. In this paper, we address the problem of…

Computer Vision and Pattern Recognition · Computer Science 2021-10-19 Benedikt Mersch , Xieyuanli Chen , Jens Behley , Cyrill Stachniss

LiDAR-based semantic perception tasks are critical yet challenging for autonomous driving. Due to the motion of objects and static/dynamic occlusion, temporal information plays an essential role in reinforcing perception by enhancing and…

Computer Vision and Pattern Recognition · Computer Science 2023-08-28 Xuechao Chen , Shuangjie Xu , Xiaoyi Zou , Tongyi Cao , Dit-Yan Yeung , Lu Fang

LiDAR point cloud analysis is a core task for 3D computer vision, especially for autonomous driving. However, due to the severe sparsity and noise interference in the single sweep LiDAR point cloud, the accurate semantic segmentation is…

Computer Vision and Pattern Recognition · Computer Science 2020-12-08 Xu Yan , Jiantao Gao , Jie Li , Ruimao Zhang , Zhen Li , Rui Huang , Shuguang Cui

Deep neural networks are widely used for understanding 3D point clouds. At each point convolution layer, features are computed from local neighborhoods of 3D points and combined for subsequent processing in order to extract semantic…

Computer Vision and Pattern Recognition · Computer Science 2021-05-13 Jiayun Wang , Rudrasis Chakraborty , Stella X. Yu

Semantic segmentation of 3D LiDAR point clouds, essential for autonomous driving and infrastructure management, is best achieved by supervised learning, which demands extensive annotated datasets and faces the problem of domain shifts. We…

Computer Vision and Pattern Recognition · Computer Science 2025-05-07 Andrew Caunes , Thierry Chateau , Vincent Frémont

To date, various 3D scene understanding tasks still lack practical and generalizable pre-trained models, primarily due to the intricate nature of 3D scene understanding tasks and their immense variations introduced by camera views,…

Computer Vision and Pattern Recognition · Computer Science 2021-09-02 Siyuan Huang , Yichen Xie , Song-Chun Zhu , Yixin Zhu

The high temporal variation of the point clouds is the key challenge of 3D single-object tracking (3D SOT). Existing approaches rely on the assumption that the shape variation of the point clouds and the motion of the objects across…

Computer Vision and Pattern Recognition · Computer Science 2024-09-09 Qiao Wu , Kun Sun , Pei An , Mathieu Salzmann , Yanning Zhang , Jiaqi Yang

The main challenge in 3D object detection from LiDAR point clouds is achieving real-time performance without affecting the reliability of the network. In other words, the detecting network must be confident enough about its predictions. In…

Computer Vision and Pattern Recognition · Computer Science 2023-01-11 Youshaa Murhij , Alexander Golodkov , Dmitry Yudin

A key challenge for autonomous vehicles is to navigate in unseen dynamic environments. Separating moving objects from static ones is essential for navigation, pose estimation, and understanding how other traffic participants are likely to…

Robotics · Computer Science 2022-06-10 Benedikt Mersch , Xieyuanli Chen , Ignacio Vizzo , Lucas Nunes , Jens Behley , Cyrill Stachniss

Existing LiDAR-Camera fusion methods have achieved strong results in 3D object detection. To address the sparsity of point clouds, previous approaches typically construct spatial pseudo point clouds via depth completion as auxiliary input…

Computer Vision and Pattern Recognition · Computer Science 2025-08-28 Jijun Wang , Yan Wu , Yujian Mo , Junqiao Zhao , Jun Yan , Yinghao Hu

Temporal information plays a pivotal role in Bird's-Eye-View (BEV) driving scene understanding, which can alleviate the visual information sparsity. However, the indiscriminate temporal fusion method will cause the barrier of feature…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Siyu Li , Jiacheng Lin , Hao Shi , Jiaming Zhang , Song Wang , You Yao , Zhiyong Li , Kailun Yang

Deep-Learning-based video recognition has shown promising improvements along with the development of large-scale datasets and spatiotemporal network architectures. In image recognition, learning spatially invariant features is a key factor…

Computer Vision and Pattern Recognition · Computer Science 2020-08-14 Taeoh Kim , Hyeongmin Lee , MyeongAh Cho , Ho Seong Lee , Dong Heon Cho , Sangyoun Lee

Steering estimation is a critical task in autonomous driving, traditionally relying on 2D image-based models. In this work, we explore the advantages of incorporating 3D spatial information through hybrid architectures that combine 3D…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 Fouad Makiyeh , Huy-Dung Nguyen , Patrick Chareyre , Ramin Hasani , Marc Blanchon , Daniela Rus

Varying density of point clouds increases the difficulty of 3D detection. In this paper, we present a context-aware dynamic network (CADNet) to capture the variance of density by considering both point context and semantic context.…

Computer Vision and Pattern Recognition · Computer Science 2020-07-29 Yonglin Tian , Lichao Huang , Xuesong Li , Kunfeng Wang , Zilei Wang , Fei-Yue Wang

Popular representation learning methods encourage feature invariance under transformations applied at the input. However, in 3D perception tasks like object localization and segmentation, outputs are naturally equivariant to some…

Computer Vision and Pattern Recognition · Computer Science 2024-04-19 Deepti Hegde , Suhas Lohit , Kuan-Chuan Peng , Michael J. Jones , Vishal M. Patel

3D LiDAR point cloud data is crucial for scene perception in computer vision, robotics, and autonomous driving. Geometric and semantic scene understanding, involving 3D point clouds, is essential for advancing autonomous driving…

Computer Vision and Pattern Recognition · Computer Science 2024-11-04 Li Li

Compressing massive LiDAR point clouds in real-time is critical to autonomous machines such as drones and self-driving cars. While most of the recent prior work has focused on compressing individual point cloud frames, this paper proposes a…

Image and Video Processing · Electrical Eng. & Systems 2020-08-18 Yu Feng , Shaoshan Liu , Yuhao Zhu

Place recognition is essential for achieving closed-loop or global positioning in autonomous vehicles and mobile robots. Despite recent advancements in place recognition using 2D cameras or 3D LiDAR, it remains to be seen how to use 4D…

Robotics · Computer Science 2025-04-08 Shouyi Lu , Guirong Zhuo , Haitao Wang , Quan Zhou , Huanyu Zhou , Renbo Huang , Minqing Huang , Lianqing Zheng , Qiang Shu

4D panoptic segmentation is a challenging but practically useful task that requires every point in a LiDAR point-cloud sequence to be assigned a semantic class label, and individual objects to be segmented and tracked over time. Existing…

Computer Vision and Pattern Recognition · Computer Science 2023-11-21 Ali Athar , Enxu Li , Sergio Casas , Raquel Urtasun

Three dimensional (3D) object recognition is becoming a key desired capability for many computer vision systems such as autonomous vehicles, service robots and surveillance drones to operate more effectively in unstructured environments.…

Computer Vision and Pattern Recognition · Computer Science 2021-08-25 Chenxi Xiao , Juan Wachs