中文
相关论文

相关论文: Can we Trust Unreliable Voxels? Exploring 3D Seman…

200 篇论文

3D semantic occupancy prediction offers an intuitive and efficient scene understanding and has attracted significant interest in autonomous driving perception. Existing approaches either rely on full supervision, which demands costly…

计算机视觉与模式识别 · 计算机科学 2026-01-23 Naiyu Fang , Zheyuan Zhou , Fayao Liu , Xulei Yang , Jiacheng Wei , Lemiao Qiu , Hongsheng Li , Guosheng Lin

Robotic perception requires the modeling of both 3D geometry and semantics. Existing methods typically focus on estimating 3D bounding boxes, neglecting finer geometric details and struggling to handle general, out-of-vocabulary objects. 3D…

计算机视觉与模式识别 · 计算机科学 2023-12-14 Xiaoyu Tian , Tao Jiang , Longfei Yun , Yucheng Mao , Huitong Yang , Yue Wang , Yilun Wang , Hang Zhao

3D semantic occupancy prediction is crucial for autonomous driving, providing a dense, semantically rich environmental representation. However, existing methods focus on in-distribution scenes, making them susceptible to Out-of-Distribution…

计算机视觉与模式识别 · 计算机科学 2026-01-13 Yuheng Zhang , Mengfei Duan , Kunyu Peng , Yuhang Wang , Ruiping Liu , Fei Teng , Kai Luo , Zhiyong Li , Kailun Yang

We introduce LOcc, an effective and generalizable framework for open-vocabulary occupancy (OVO) prediction. Previous approaches typically supervise the networks through coarse voxel-to-text correspondences via image features as…

计算机视觉与模式识别 · 计算机科学 2025-07-31 Zhu Yu , Bowen Pang , Lizhe Liu , Runmin Zhang , Qiang Li , Si-Yuan Cao , Maochun Luo , Mingxia Chen , Sheng Yang , Hui-Liang Shen

Semantic occupancy has recently gained significant traction as a prominent 3D scene representation. However, most existing methods rely on large and costly datasets with fine-grained 3D voxel labels for training, which limits their…

计算机视觉与模式识别 · 计算机科学 2024-02-21 Simon Boeder , Fabian Gigengack , Benjamin Risse

In perception for automated vehicles, safety is critical not only for the driver but also for other agents in the scene, particularly vulnerable road users such as pedestrians and cyclists. Previous representation methods, such as Bird's…

计算机视觉与模式识别 · 计算机科学 2026-03-27 Seamie Hayes , Ganesh Sistu , Tim Brophy , Ciaran Eising

3D semantic occupancy prediction aims to reconstruct the 3D geometry and semantics of the surrounding environment. With dense voxel labels, prior works typically formulate it as a dense segmentation task, independently classifying each…

图形学 · 计算机科学 2025-06-06 Wuyang Li , Zhu Yu , Alexandre Alahi

3D occupancy prediction holds significant promise in the fields of robot perception and autonomous driving, which quantifies 3D scenes into grid cells with semantic labels. Recent works mainly utilize complete occupancy labels in 3D voxel…

计算机视觉与模式识别 · 计算机科学 2024-03-05 Mingjie Pan , Jiaming Liu , Renrui Zhang , Peixiang Huang , Xiaoqi Li , Bing Wang , Hongwei Xie , Li Liu , Shanghang Zhang

Inferring the 3D structure from a single image, particularly in occluded regions, remains a fundamental yet unsolved challenge in vision-centric autonomous driving. Existing unsupervised approaches typically train a neural radiance field…

计算机视觉与模式识别 · 计算机科学 2026-02-09 Zizhan Guo , Yi Feng , Mengtan Zhang , Haoran Zhang , Wei Ye , Rui Fan

3D occupancy prediction (3DOcc) is a rapidly rising and challenging perception task in the field of autonomous driving. Existing 3D occupancy networks (OccNets) are both computationally heavy and label-hungry. In terms of model complexity,…

计算机视觉与模式识别 · 计算机科学 2025-04-09 Yining Shi , Kun Jiang , Jinyu Miao , Ke Wang , Kangan Qian , Yunlong Wang , Jiusi Li , Tuopu Wen , Mengmeng Yang , Yiliang Xu , Diange Yang

Self-supervised 3D occupancy prediction offers a promising solution for understanding complex driving scenes without requiring costly 3D annotations. However, training dense occupancy decoders to capture fine-grained geometry and semantics…

计算机视觉与模式识别 · 计算机科学 2026-03-19 Fengyi Zhang , Xiangyu Sun , Huitong Yang , Zheng Zhang , Zi Huang , Yadan Luo

Learning with noisy labels (LNL) is typically benchmarked by closed-set classification accuracy, yet deployment often requires classifiers to reject out-of-distribution (OOD) inputs. We present a learner-agnostic ACC-OOD benchmark that…

机器学习 · 计算机科学 2026-05-19 Ningkang Peng , Jingyang Mao , Runhan Zhou , Peirong Ma , Yanhui Gu

3D occupancy prediction is an important task for the robustness of vision-centric autonomous driving, which aims to predict whether each point is occupied in the surrounding 3D space. Existing methods usually require 3D occupancy labels to…

计算机视觉与模式识别 · 计算机科学 2023-11-30 Yuanhui Huang , Wenzhao Zheng , Borui Zhang , Jie Zhou , Jiwen Lu

Accurate 3D perception is essential for understanding the environment in autonomous driving. Recent advancements in 3D semantic occupancy prediction have leveraged camera-LiDAR fusion to improve robustness and accuracy. However, current…

计算机视觉与模式识别 · 计算机科学 2024-12-31 Minjae Seong , Jisong Kim , Geonho Bang , Hawook Jeong , Jun Won Choi

Vision-centric semantic occupancy prediction plays a crucial role in autonomous driving, which requires accurate and reliable predictions from low-cost sensors. Although having notably narrowed the accuracy gap with LiDAR, there is still…

计算机视觉与模式识别 · 计算机科学 2024-09-27 Song Wang , Zhongdao Wang , Jiawei Yu , Wentong Li , Bailan Feng , Junbo Chen , Jianke Zhu

In autonomous driving, 3D occupancy prediction outputs voxel-wise status and semantic labels for more comprehensive understandings of 3D scenes compared with traditional perception tasks, such as 3D object detection and bird's-eye view…

计算机视觉与模式识别 · 计算机科学 2024-03-06 Jiawei Hou , Xiaoyan Li , Wenhao Guan , Gang Zhang , Di Feng , Yuheng Du , Xiangyang Xue , Jian Pu

3D semantic occupancy prediction has emerged as a critical perception task for autonomous driving due to its ability to offer voxel-level semantic and geometric understanding of the environment. However, such a refined representation for…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Hanlin Wu , Pengfei Lin , Ehsan Javanmardi , Naren Bao , Bo Qian , Hao Si , Manabu Tsukada

The 3D occupancy estimation task has become an important challenge in the area of vision-based autonomous driving recently. However, most existing camera-based methods rely on costly 3D voxel labels or LiDAR scans for training, limiting…

计算机视觉与模式识别 · 计算机科学 2024-07-26 Simon Boeder , Fabian Gigengack , Benjamin Risse

Developing 3D semantic occupancy prediction models often relies on dense 3D annotations for supervised learning, a process that is both labor and resource-intensive, underscoring the need for label-efficient or even label-free approaches.…

计算机视觉与模式识别 · 计算机科学 2025-04-04 Samuel Sze , Daniele De Martini , Lars Kunze

In this technical report, we present our solution, named UniOCC, for the Vision-Centric 3D occupancy prediction track in the nuScenes Open Dataset Challenge at CVPR 2023. Existing methods for occupancy prediction primarily focus on…

计算机视觉与模式识别 · 计算机科学 2023-06-16 Mingjie Pan , Li Liu , Jiaming Liu , Peixiang Huang , Longlong Wang , Shanghang Zhang , Shaoqing Xu , Zhiyi Lai , Kuiyuan Yang
‹ 上一页 1 2 3 10 下一页 ›