中文
相关论文

相关论文: FastRSR: Efficient and Accurate Road Surface Recon…

200 篇论文

Dynamic scene reconstruction for autonomous driving enables vehicles to perceive and interpret complex scene changes more precisely. Dynamic Neural Radiance Fields (NeRFs) have recently shown promising capability in scene modeling. However,…

计算机视觉与模式识别 · 计算机科学 2025-05-15 Yue Wen , Liang Song , Yijia Liu , Siting Zhu , Yanzi Miao , Lijun Han , Hesheng Wang

An autonomous system's perception engine must provide an accurate understanding of the environment for it to make decisions. Deep learning based object detection networks experience degradation in the performance and robustness for small…

计算机视觉与模式识别 · 计算机科学 2022-10-10 Hemant Kumawat , Saibal Mukhopadhyay

Accurate 3D object detection for autonomous driving requires complementary sensors. Cameras provide dense semantics but unreliable depth, while millimeter-wave radar offers precise range and velocity measurements with sparse geometry. We…

计算机视觉与模式识别 · 计算机科学 2026-04-07 Mayank Mayank , Bharanidhar Duraisamy , Florian Geiß , Abhinav Valada

Camera-based bird-eye-view (BEV) perception paradigm has made significant progress in the autonomous driving field. Under such a paradigm, accurate BEV representation construction relies on reliable depth estimation for multi-camera images.…

计算机视觉与模式识别 · 计算机科学 2023-12-14 Yang Jiao , Zequn Jie , Shaoxiang Chen , Lechao Cheng , Jingjing Chen , Lin Ma , Yu-Gang Jiang

Radars and cameras belong to the most frequently used sensors for advanced driver assistance systems and automated driving research. However, there has been surprisingly little research on radar-camera fusion with neural networks. One of…

计算机视觉与模式识别 · 计算机科学 2023-09-29 Lukas Stäcker , Shashank Mishra , Philipp Heidenreich , Jason Rambach , Didier Stricker

With the rapid advancement of autonomous driving technology, there is a growing need for enhanced safety and efficiency in the automatic environmental perception of vehicles during their operation. In modern vehicle setups, cameras and…

计算机视觉与模式识别 · 计算机科学 2024-06-04 Di Wu , Feng Yang , Benlian Xu , Pan Liao , Bo Liu

Trajectory prediction is, naturally, a key task for vehicle autonomy. While the number of traffic rules is limited, the combinations and uncertainties associated with each agent's behaviour in real-world scenarios are nearly impossible to…

计算机视觉与模式识别 · 计算机科学 2023-12-21 Sushil Sharma , Arindam Das , Ganesh Sistu , Mark Halton , Ciarán Eising

Existing LiDAR-based 3D object detection methods for autonomous driving scenarios mainly adopt the training-from-scratch paradigm. Unfortunately, this paradigm heavily relies on large-scale labeled data, whose collection can be expensive…

计算机视觉与模式识别 · 计算机科学 2024-01-23 Zhiwei Lin , Yongtao Wang , Shengxiang Qi , Nan Dong , Ming-Hsuan Yang

Novel view synthesis from monocular videos of dynamic scenes with unknown camera poses remains a fundamental challenge in computer vision and graphics. While recent advances in 3D representations such as Neural Radiance Fields (NeRF) and 3D…

计算机视觉与模式识别 · 计算机科学 2025-11-10 Mengqi Guo , Bo Xu , Yanyan Li , Gim Hee Lee

3D object detection is essential for autonomous driving. As an emerging sensor, 4D imaging radar offers advantages as low cost, long-range detection, and accurate velocity measurement, making it highly suitable for object detection.…

计算机视觉与模式识别 · 计算机科学 2025-10-23 Xiaozhi Li , Huijun Di , Jian Li , Feng Liu , Wei Liang

Realtime 4D reconstruction for dynamic scenes remains a crucial challenge for autonomous driving perception. Most existing methods rely on depth estimation through self-supervision or multi-modality sensor fusion. In this paper, we propose…

计算机视觉与模式识别 · 计算机科学 2024-12-10 Xin Fei , Wenzhao Zheng , Yueqi Duan , Wei Zhan , Masayoshi Tomizuka , Kurt Keutzer , Jiwen Lu

In advanced paradigms of autonomous driving, learning Bird's Eye View (BEV) representation from surrounding views is crucial for multi-task framework. However, existing methods based on depth estimation or camera-driven attention are not…

计算机视觉与模式识别 · 计算机科学 2022-11-01 Hongxiang Jiang , Wenming Meng , Hongmei Zhu , Qian Zhang , Jihao Yin

3D object detection based on LiDAR point clouds is a crucial module in autonomous driving particularly for long range sensing. Most of the research is focused on achieving higher accuracy and these models are not optimized for deployment on…

计算机视觉与模式识别 · 计算机科学 2021-07-13 Sambit Mohapatra , Senthil Yogamani , Heinrich Gotzig , Stefan Milz , Patrick Mader

Understanding road geometry is a critical component of the autonomous vehicle (AV) stack. While high-definition (HD) maps can readily provide such information, they suffer from high labeling and maintenance costs. Accordingly, many recent…

机器人学 · 计算机科学 2024-07-10 Xunjiang Gu , Guanyu Song , Igor Gilitschenski , Marco Pavone , Boris Ivanovic

Image-to-point cloud cross-modal Visual Place Recognition (VPR) is a challenging task where the query is an RGB image, and the database samples are LiDAR point clouds. Compared to single-modal VPR, this approach benefits from the widespread…

计算机视觉与模式识别 · 计算机科学 2025-03-03 Jianyi Peng , Fan Lu , Bin Li , Yuan Huang , Sanqing Qu , Guang Chen

3D Gaussian Splatting (3DGS) has shown great potential in autonomous driving simulation and data generation, enabling photorealistic reconstruction and flexible scene manipulation. However, existing 3DGS scene editing methods have limited…

计算机视觉与模式识别 · 计算机科学 2026-05-26 Feng Zhou , Jian Zhang , Yuhang Sun , He Wang , Qiong Wen , Debao Kong , Tieru Wu , Rui Ma

Single-view 3D shape retrieval is a fundamental yet challenging task that is increasingly important with the growth of available 3D data. Existing approaches largely fall into two categories: those using contrastive learning to map point…

计算机视觉与模式识别 · 计算机科学 2026-04-30 Jiaxin Shi , Guofeng Zhang , Wufei Ma , Naifu Liang , Adam Kortylewski , Alan Yuille

Although multi-view 3D object detection based on the Bird's-Eye-View (BEV) paradigm has garnered widespread attention as an economical and deployment-friendly perception solution for autonomous driving, there is still a performance gap…

计算机视觉与模式识别 · 计算机科学 2024-07-16 Zheng Jiang , Jinqing Zhang , Yanan Zhang , Qingjie Liu , Zhenghui Hu , Baohui Wang , Yunhong Wang

Recent sparse multi-view scene reconstruction advances like DUSt3R and MASt3R no longer require camera calibration and camera pose estimation. However, they only process a pair of views at a time to infer pixel-aligned pointmaps. When…

计算机视觉与模式识别 · 计算机科学 2024-12-11 Zhenggang Tang , Yuchen Fan , Dilin Wang , Hongyu Xu , Rakesh Ranjan , Alexander Schwing , Zhicheng Yan

Multi-view 3D reconstruction remains a core challenge in computer vision, particularly in applications requiring accurate and scalable representations across diverse perspectives. Current leading methods such as DUSt3R employ a…

计算机视觉与模式识别 · 计算机科学 2025-03-21 Jianing Yang , Alexander Sax , Kevin J. Liang , Mikael Henaff , Hao Tang , Ang Cao , Joyce Chai , Franziska Meier , Matt Feiszli