中文
相关论文

相关论文: TopoMaskV3: 3D Mask Head with Dense Offset and Hei…

200 篇论文

Recently, the centerline has become a popular representation of lanes due to its advantages in solving the road topology problem. To enhance centerline prediction, we have developed a new approach called TopoMask. Unlike previous methods…

计算机视觉与模式识别 · 计算机科学 2024-09-18 M. Esat Kalfaoglu , Halil Ibrahim Ozturk , Ozsel Kilinc , Alptekin Temizel

3D lane detection and topology reasoning are essential tasks in autonomous driving scenarios, requiring not only detecting the accurate 3D coordinates on lane lines, but also reasoning the relationship between lanes and traffic elements.…

计算机视觉与模式识别 · 计算机科学 2024-06-06 Han Li , Zehao Huang , Zitian Wang , Wenge Rong , Naiyan Wang , Si Liu

Driving scene understanding task involves detecting static elements such as lanes, traffic signs, and traffic lights, and their relationships with each other. To facilitate the development of comprehensive scene understanding solutions…

计算机视觉与模式识别 · 计算机科学 2023-06-09 M. Esat Kalfaoglu , Halil Ibrahim Ozturk , Ozsel Kilinc , Alptekin Temizel

We introduce a pioneering approach to self-supervised learning for point clouds, employing a geometrically informed mask selection strategy called GeoMask3D (GM3D) to boost the efficiency of Masked Auto Encoders (MAE). Unlike the…

Recent advances in dense 3D reconstruction have led to significant progress, yet achieving accurate unified geometric prediction remains a major challenge. Most existing methods are limited to predicting a single geometry quantity from…

计算机视觉与模式识别 · 计算机科学 2025-07-23 Xianze Fang , Jingnan Gao , Zhe Wang , Zhuo Chen , Xingyu Ren , Jiangjing Lyu , Qiaomu Ren , Zhonglei Yang , Xiaokang Yang , Yichao Yan , Chengfei Lyu

Traditional closed-set 3D detection frameworks fail to meet the demands of open-world applications like autonomous driving. Existing open-vocabulary 3D detection methods typically adopt a two-stage pipeline consisting of pseudo-label…

计算机视觉与模式识别 · 计算机科学 2025-08-19 Qi Liu , Yabei Li , Hongsong Wang , Lei He

In the existing methods, LiDAR odometry shows superior performance, but visual odometry is still widely used for its price advantage. Conventionally, the task of visual odometry mainly rely on the input of continuous images. However, it is…

计算机视觉与模式识别 · 计算机科学 2022-09-07 Huiying Deng , Guangming Wang , Zhiheng Feng , Chaokang Jiang , Xinrui Wu , Yanzi Miao , Hesheng Wang

Generalizing open-vocabulary 3D instance segmentation (OV-3DIS) to diverse, unstructured, and mesh-free environments is crucial for robotics and AR/VR, yet remains a significant challenge. We attribute this to two key limitations of…

计算机视觉与模式识别 · 计算机科学 2026-05-15 Zhishan Zhou , Siyuan Wei , Zengran Wang , Chunjie Wang , Xiaosheng Yan , Xiao Liu

Understanding road topology is crucial for autonomous driving. This paper introduces TopoBDA (Topology with Bezier Deformable Attention), a novel approach that enhances road topology comprehension by leveraging Bezier Deformable Attention…

计算机视觉与模式识别 · 计算机科学 2026-01-09 Muhammet Esat Kalfaoglu , Halil Ibrahim Ozturk , Ozsel Kilinc , Alptekin Temizel

Topology reasoning, which unifies perception and structured reasoning, plays a vital role in understanding intersections for autonomous driving. However, its performance heavily relies on the accuracy of lane detection, particularly at…

计算机视觉与模式识别 · 计算机科学 2025-05-26 Yanping Fu , Xinyuan Liu , Tianyu Li , Yike Ma , Yucheng Zhang , Feng Dai

Road-boundary detection is important for autonomous driving. It can be used to constrain autonomous vehicles running on road areas to ensure driving safety. Compared with online road-boundary detection using on-vehicle cameras/Lidars,…

计算机视觉与模式识别 · 计算机科学 2021-07-05 Zhenhua Xu , Yuxiang Sun , Ming Liu

Unsupervised contrastive learning for indoor-scene point clouds has achieved great successes. However, unsupervised learning point clouds in outdoor scenes remains challenging because previous methods need to reconstruct the whole scene and…

计算机视觉与模式识别 · 计算机科学 2026-03-02 Runjian Chen , Yao Mu , Runsen Xu , Wenqi Shao , Chenhan Jiang , Hang Xu , Zhenguo Li , Ping Luo

The dominant paradigm for high-fidelity 3D generation relies on a VAE-Diffusion pipeline, where the VAE's reconstruction capability sets a firm upper bound on generation quality. A fundamental challenge limiting existing VAEs is the…

计算机视觉与模式识别 · 计算机科学 2026-03-27 Guan Luo , Xiu Li , Rui Chen , Xuanyu Yi , Jing Lin , Chia-Hao Chen , Jiahang Liu , Song-Hai Zhang , Jianfeng Zhang

3D semantic occupancy prediction is an essential part of autonomous driving, focusing on capturing the geometric details of scenes. Off-road environments are rich in geometric information, therefore it is suitable for 3D semantic occupancy…

计算机视觉与模式识别 · 计算机科学 2024-10-29 Heng Zhai , Jilin Mei , Chen Min , Liang Chen , Fangzhou Zhao , Yu Hu

Topology reasoning aims to comprehensively understand road scenes and present drivable routes in autonomous driving. It requires detecting road centerlines (lane) and traffic elements, further reasoning their topology relationship, i.e.,…

计算机视觉与模式识别 · 计算机科学 2023-11-02 Dongming Wu , Jiahao Chang , Fan Jia , Yingfei Liu , Tiancai Wang , Jianbing Shen

Object recognition has seen significant progress in the image domain, with focus primarily on 2D perception. We propose to leverage existing large-scale datasets of 3D models to understand the underlying 3D structure of objects seen in an…

计算机视觉与模式识别 · 计算机科学 2020-07-28 Weicheng Kuo , Anelia Angelova , Tsung-Yi Lin , Angela Dai

Point cloud segmentation is a fundamental task in 3D scene understanding. Its progress is constrained by the high cost and time required for dense 3D annotations, making labeled samples difficult to obtain. Beyond annotation scarcity,…

计算机视觉与模式识别 · 计算机科学 2026-05-29 Thenukan Pathmanathan , Kanchan Keisham , Thangarajah Akilan

We present PI3DETR, an end-to-end framework that directly predicts 3D parametric curve instances from raw point clouds, avoiding the intermediate representations and multi-stage processing common in prior work. Extending 3DETR, our model…

计算机视觉与模式识别 · 计算机科学 2026-01-14 Fabio F. Oberweger , Michael Schwingshackl , Vanessa Staderini

State-of-the-art methods for driving-scene LiDAR-based perception (including point cloud semantic segmentation, panoptic segmentation and 3D detection, \etc) often project the point clouds to 2D space and then process them via 2D…

计算机视觉与模式识别 · 计算机科学 2021-09-14 Xinge Zhu , Hui Zhou , Tai Wang , Fangzhou Hong , Wei Li , Yuexin Ma , Hongsheng Li , Ruigang Yang , Dahua Lin

Accurate 3D lane estimation is crucial for ensuring safety in autonomous driving. However, prevailing monocular techniques suffer from depth loss and lighting variations, hampering accurate 3D lane detection. In contrast, LiDAR points offer…

计算机视觉与模式识别 · 计算机科学 2024-06-25 Yueru Luo , Shuguang Cui , Zhen Li
‹ 上一页 1 2 3 10 下一页 ›