中文
相关论文

相关论文: NRSeg: Noise-Resilient Learning for BEV Semantic S…

200 篇论文

Accurate BEV semantic segmentation from fisheye imagery remains challenging due to extreme non-linear distortion, occlusion, and depth ambiguity inherent to wide-angle projections. We present a distortion-aware BEV segmentation framework…

计算机视觉与模式识别 · 计算机科学 2025-11-24 Shubham Sonarghare , Prasad Deshpande , Ciaran Hogan , Deepika-Rani Kaliappan-Mahalingam , Ganesh Sistu

Current point-based approaches encounter limitations in scalability and rendering quality when using large 3D point cloud maps because using them directly for novel view synthesis (NVS) leads to degraded visualizations. We identify the…

计算机视觉与模式识别 · 计算机科学 2025-04-29 Mohammad Altillawi , Fengyi Shen , Liudi Yang , Sai Manoj Prakhya , Ziyuan Liu

With the rapid advancement of autonomous driving, vehicle perception, particularly detection and segmentation, has placed increasingly higher demands on algorithmic performance. Pre-trained large segmentation models, especially Segment…

计算机视觉与模式识别 · 计算机科学 2025-08-07 Xiao Wang , Ziwen Wang , Wentao Wu , Anjie Wang , Jiashu Wu , Yantao Pan , Chenglong Li

Road intersection monitoring and control research often utilize bird's eye view (BEV) simulators. In real traffic settings, achieving a BEV akin to that in a simulator necessitates the deployment of drones or specific sensor mounting, which…

计算机视觉与模式识别 · 计算机科学 2024-08-15 Rukesh Prajapati , Amr S. El-Wakeel

Bird's Eye View (BEV) is a popular representation for processing 3D point clouds, and by its nature is fundamentally sparse. Motivated by the computational limitations of mobile robot platforms, we create a fast, high-performance BEV 3D…

计算机视觉与模式识别 · 计算机科学 2022-08-02 Kyle Vedder , Eric Eaton

Pixel-level vision tasks, such as semantic segmentation, require extensive and high-quality annotated data, which is costly to obtain. Semi-supervised semantic segmentation (SSSS) has emerged as a solution to alleviate the labeling burden…

计算机视觉与模式识别 · 计算机科学 2025-07-22 Danhui Chen , Ziquan Liu , Chuxi Yang , Dan Wang , Yan Yan , Yi Xu , Xiangyang Ji

Recent advancements in Bird's Eye View (BEV) fusion for map construction have demonstrated remarkable mapping of urban environments. However, their deep and bulky architecture incurs substantial amounts of backpropagation memory and…

计算机视觉与模式识别 · 计算机科学 2024-08-23 Minsu Kim , Giseop Kim , Sunwook Choi

Recent advances in appearance-based models have shown improved eye tracking performance in difficult scenarios like occlusion due to eyelashes, eyelids or camera placement, and environmental reflections on the cornea and glasses. The key…

计算机视觉与模式识别 · 计算机科学 2021-03-18 Aayush K. Chaudhary , Prashnna K. Gyawali , Linwei Wang , Jeff B. Pelz

Integrating LiDAR and camera information in the bird's eye view (BEV) representation has demonstrated its effectiveness in 3D object detection. However, because of the fundamental disparity in geometric accuracy between these sensors,…

计算机视觉与模式识别 · 计算机科学 2025-12-03 Guowen Zhang , Chenhang He , Liyi Chen , Lei Zhang

Bird's-Eye View (BEV) features are popular intermediate scene representations shared by the 3D backbone and the detector head in LiDAR-based object detectors. However, little research has been done to investigate how to incorporate…

计算机视觉与模式识别 · 计算机科学 2023-04-05 Haitao Yang , Zaiwei Zhang , Xiangru Huang , Min Bai , Chen Song , Bo Sun , Li Erran Li , Qixing Huang

Open-vocabulary semantic segmentation (OVSS) involves assigning labels to each pixel in an image based on textual descriptions, leveraging world models like CLIP. However, they encounter significant challenges in cross-domain…

计算机视觉与模式识别 · 计算机科学 2025-06-05 Aniruddh Sikdar , Aditya Gandhamal , Suresh Sundaram

Semantic image and video segmentation stand among the most important tasks in computer vision nowadays, since they provide a complete and meaningful representation of the environment by means of a dense classification of the pixels in a…

计算机视觉与模式识别 · 计算机科学 2023-03-09 Felipe Manfio Barbosa , Fernando Santos Osório

Open-vocabulary remote sensing image segmentation (OVRSIS) remains underexplored due to fragmented datasets, limited training diversity, and the lack of evaluation benchmarks that reflect realistic geospatial application demands. Our…

计算机视觉与模式识别 · 计算机科学 2026-04-20 Bingyu Li , Tao Huo , Haocheng Dong , Da Zhang , Zhiyuan Zhao , Junyu Gao , Xuelong Li

Autonomous driving systems face significant challenges in perceiving complex environments and making real-time decisions. Traditional modular approaches, while offering interpretability, suffer from error propagation and coordination…

人工智能 · 计算机科学 2025-08-11 Siyi Lu , Run Liu , Dongsheng Yang , Lei He

Augmented Reality (AR) devices, emerging as prominent mobile interaction platforms, face challenges in user safety, particularly concerning oncoming vehicles. While some solutions leverage onboard camera arrays, these cameras often have…

计算机视觉与模式识别 · 计算机科学 2024-09-06 Renjie Wu , Hu Wang , Feras Dayoub , Hsiang-Ting Chen

The advancement of vision-only Bird's-Eye-View (BEV) perception, a core paradigm for cost-effective autonomous driving, is hindered by the long-standing fundamental trade-off between perception accuracy and on-device deployment efficiency.…

计算机视觉与模式识别 · 计算机科学 2026-05-20 Yuanpeng Chen , Hui Song , Sheng Yang , Wei Tao , Shanhui Mo , Shuang Zhang , Xiao Hua , Tiankun Zhao

The reasoning segmentation task involves segmenting objects within an image by interpreting implicit user instructions, which may encompass subtleties such as contextual cues and open-world knowledge. Despite significant advancements made…

计算机视觉与模式识别 · 计算机科学 2025-08-14 Weihuang Lin , Yiwei Ma , Xiaoshuai Sun , Shuting He , Jiayi Ji , Liujuan Cao , Rongrong Ji

Semantic segmentation takes pivotal roles in various applications such as autonomous driving and medical image analysis. When deploying segmentation models in practice, it is critical to test their behaviors in varied and complex scenes in…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Zijin Yin , Bing Li , Kongming Liang , Hao Sun , Zhongjiang He , Zhanyu Ma , Jun Guo

In this paper, we introduce Mask2Map, a novel end-to-end online HD map construction method designed for autonomous driving applications. Our approach focuses on predicting the class and ordered point set of map instances within a scene,…

计算机视觉与模式识别 · 计算机科学 2024-12-13 Sehwan Choi , Jungho Kim , Hongjae Shin , Jun Won Choi

3D segmentation is a core problem in computer vision and, similarly to many other dense prediction tasks, it requires large amounts of annotated data for adequate training. However, densely labeling 3D point clouds to employ…

计算机视觉与模式识别 · 计算机科学 2024-09-13 Ozan Unal , Christos Sakaridis , Luc Van Gool
‹ 上一页 1 8 9 10 下一页 ›