English
Related papers

Related papers: FSD V2: Improving Fully Sparse 3D Object Detection…

200 papers

Designing an efficient yet deployment-friendly 3D backbone to handle sparse point clouds is a fundamental problem in 3D perception. Compared with the customized sparse convolution, the attention mechanism in Transformers is more appropriate…

Computer Vision and Pattern Recognition · Computer Science 2023-03-21 Haiyang Wang , Chen Shi , Shaoshuai Shi , Meng Lei , Sen Wang , Di He , Bernt Schiele , Liwei Wang

The multi-line LiDAR is widely used in autonomous vehicles, so point cloud-based 3D detectors are essential for autonomous driving. Extracting rich multi-scale features is crucial for point cloud-based 3D detectors in autonomous driving due…

Computer Vision and Pattern Recognition · Computer Science 2024-11-14 Xusheng Li , Chengliang Wang , Shumao Wang , Zhuo Zeng , Ji Liu

Recently, promising applications in robotics and augmented reality have attracted considerable attention to 3D object detection from point clouds. In this paper, we present FCAF3D - a first-in-class fully convolutional anchor-free indoor 3D…

Computer Vision and Pattern Recognition · Computer Science 2022-03-25 Danila Rukhovich , Anna Vorontsova , Anton Konushin

Bird-eye-view (BEV) based methods have made great progress recently in multi-view 3D detection task. Comparing with BEV based methods, sparse based methods lag behind in performance, but still have lots of non-negligible merits. To push…

Computer Vision and Pattern Recognition · Computer Science 2023-02-13 Xuewu Lin , Tianwei Lin , Zixiang Pei , Lichao Huang , Zhizhong Su

We present \textit{VoxelKP}, a novel fully sparse network architecture tailored for human keypoint estimation in LiDAR data. The key challenge is that objects are distributed sparsely in 3D space, while human keypoint detection requires…

Computer Vision and Pattern Recognition · Computer Science 2023-12-15 Jian Shi , Peter Wonka

Humans can easily imagine the complete 3D geometry of occluded objects and scenes. This appealing ability is vital for recognition and understanding. To enable such capability in AI systems, we propose VoxFormer, a Transformer-based…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Yiming Li , Zhiding Yu , Christopher Choy , Chaowei Xiao , Jose M. Alvarez , Sanja Fidler , Chen Feng , Anima Anandkumar

Recent advances in sparse voxel representations have significantly improved the quality of 3D content generation, enabling high-resolution modeling with fine-grained geometry. However, existing frameworks suffer from severe computational…

Computer Vision and Pattern Recognition · Computer Science 2025-08-01 Yiwen Chen , Zhihao Li , Yikai Wang , Hu Zhang , Qin Li , Chi Zhang , Guosheng Lin

LiDAR has become one of the primary 3D object detection sensors in autonomous driving. However, LiDAR's diverging point pattern with increasing distance results in a non-uniform sampled point cloud ill-suited to discretized volumetric…

Computer Vision and Pattern Recognition · Computer Science 2022-03-23 Jordan S. K. Hu , Tianshu Kuai , Steven L. Waslander

Recent advancements in open-vocabulary 3D scene understanding heavily rely on 3D Gaussian Splatting (3DGS) to register vision-language features into 3D space. However, we identify two critical limitations in these approaches: the spatial…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Fusang Wang , Nathan Piasco , Moussab Bennehar , Luis Roldão , Dzmitry Tsishkou , Fabien Moutarde

A unified neural network structure is presented for joint 3D object detection and point cloud segmentation in this paper. We leverage rich supervision from both detection and segmentation labels rather than using just one of them. In…

Computer Vision and Pattern Recognition · Computer Science 2021-11-16 Yuanxin Zhong , Minghan Zhu , Huei Peng

Reconstructing accurate surfaces with radiance fields has achieved remarkable progress in recent years. However, prevailing approaches, primarily based on Gaussian Splatting, are increasingly constrained by representational bottlenecks. In…

Computer Vision and Pattern Recognition · Computer Science 2025-11-10 Jiahe Li , Jiawei Zhang , Youmin Zhang , Xiao Bai , Jin Zheng , Xiaohan Yu , Lin Gu

LiDAR is an important method for autonomous driving systems to sense the environment. The point clouds obtained by LiDAR typically exhibit sparse and irregular distribution, thus posing great challenges to the detection of 3D objects,…

Computer Vision and Pattern Recognition · Computer Science 2020-10-28 Tai Wang , Xinge Zhu , Dahua Lin

Multi-view 3D object detection is a fundamental task in autonomous driving perception, where achieving a balance between detection accuracy and computational efficiency remains crucial. Sparse query-based 3D detectors efficiently aggregate…

Computer Vision and Pattern Recognition · Computer Science 2025-12-22 Di Wu , Feng Yang , Wenhui Zhao , Jinwen Yu , Pan Liao , Benlian Xu , Dingwen Zhang

Existing LiDAR 3D object detection methods predominantely rely on sparse convolutions and/or transformers, which can be challenging to run on resource-constrained edge devices, due to irregular memory access patterns and high computational…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Shizhong Han , Hsin-Pai Cheng , Hong Cai , Jihad Masri , Soyeb Nagori , Fatih Porikli

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

Camera relocalization methods range from dense image alignment to direct camera pose regression from a query image. Among these, sparse feature matching stands out as an efficient, versatile, and generally lightweight approach with numerous…

Computer Vision and Pattern Recognition · Computer Science 2025-05-22 Vincenzo Polizzi , Marco Cannici , Davide Scaramuzza , Jonathan Kelly

Sparse 3D detectors have received significant attention since the query-based paradigm embraces low latency without explicit dense BEV feature construction. However, these detectors achieve worse performance than their dense counterparts.…

Computer Vision and Pattern Recognition · Computer Science 2024-07-11 Hongcheng Zhang , Liu Liang , Pengxin Zeng , Xiao Song , Zhe Wang

We propose an efficient radiance field rendering algorithm that incorporates a rasterization process on adaptive sparse voxels without neural networks or 3D Gaussians. There are two key contributions coupled with the proposed system. The…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Cheng Sun , Jaesung Choe , Charles Loop , Wei-Chiu Ma , Yu-Chiang Frank Wang

Reconstructing 3D objects from extremely sparse views is a long-standing and challenging problem. While recent techniques employ image diffusion models for generating plausible images at novel viewpoints or for distilling pre-trained…

Computer Vision and Pattern Recognition · Computer Science 2023-12-21 Zi-Xin Zou , Weihao Cheng , Yan-Pei Cao , Shi-Sheng Huang , Ying Shan , Song-Hai Zhang

Current self-supervised learning (SSL) methods (e.g., SimCLR, DINO, VICReg,MOCOv3) target primarily on representations at instance level and do not generalize well to dense prediction tasks, such as object detection and segmentation.Towards…

Machine Learning · Computer Science 2023-11-07 Qing Su , Anton Netchaev , Hai Li , Shihao Ji