English
Related papers

Related papers: OccFormer: Dual-path Transformer for Vision-based …

200 papers

The prediction of 3D semantic occupancy enables autonomous vehicles (AVs) to perceive the fine-grained geometric and semantic scene structure for safe navigation and decision-making. Existing methods mainly rely on either voxel-based…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Zhenxing Ming , Yaoqi Huang , Julie Stephany Berrio , Mao Shan , Stewart Worrall

In the realm of autonomous vehicle perception, comprehending 3D scenes is paramount for tasks such as planning and mapping. Camera-based 3D Semantic Occupancy Prediction (OCC) aims to infer scene geometry and semantics from limited…

Computer Vision and Pattern Recognition · Computer Science 2025-02-03 Sanbao Su , Nuo Chen , Chenchen Lin , Felix Juefei-Xu , Chen Feng , Fei Miao

This report presents our Le3DE2E_Occ solution for 4D Occupancy Forecasting in Argoverse Challenges at CVPR 2023 Workshop on Autonomous Driving (WAD). Our solution consists of a strong LiDAR-based Bird's Eye View (BEV) encoder with temporal…

Computer Vision and Pattern Recognition · Computer Science 2023-11-28 Pengfei Zheng , Kanokphan Lertniphonphan , Feng Chen , Siwei Chen , Bingchuan Sun , Jun Xie , Zhepeng Wang

The completion, extension, and generation of 3D semantic scenes are an interrelated set of capabilities that are useful for robotic navigation and exploration. Existing approaches seek to decouple these problems and solve them one-off.…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Xujia Zhang , Brendan Crowe , Christoffer Heckman

The sparse object detection paradigm shift towards dense 3D semantic occupancy prediction is necessary for dealing with long-tail safety challenges for autonomous vehicles. Nonetheless, the current voxelization methods commonly suffer from…

Computer Vision and Pattern Recognition · Computer Science 2026-01-22 A. Enes Doruk

Open-vocabulary 3D occupancy is vital for embodied agents, which need to understand complex indoor environments where semantic categories are abundant and evolve beyond fixed taxonomies. While recent work has explored open-vocabulary…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Changqing Zhou , Yueru Luo , Han Zhang , Zeyu Jiang , Changhao Chen

Relying on in-domain annotations and precise sensor-rig priors, existing 3D occupancy prediction methods are limited in both scalability and out-of-domain generalization. While recent visual geometry foundation models exhibit strong…

Computer Vision and Pattern Recognition · Computer Science 2026-03-25 Anh-Quan Cao , Tuan-Hung Vu

The choice of representation plays a key role in self-driving. Bird's eye view (BEV) representations have shown remarkable performance in recent years. In this paper, we propose to learn object-centric representations in BEV to distill a…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Shadi Hamdan , Fatma Güney

Obtaining high-quality 3D semantic occupancy from raw sensor data remains an essential yet challenging task, often requiring extensive manual labeling. In this work, we propose AutoOcc, a vision-centric automated pipeline for open-ended…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Xiaoyu Zhou , Jingqi Wang , Yongtao Wang , Yufei Wei , Nan Dong , Ming-Hsuan Yang

3D occupancy infers fine-grained 3D geometry and semantics which is critical for autonomous driving. Most existing approaches carry high compute costs, requiring dense 3D feature volume and cross-attention to effectively aggregate…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Yunxiao Shi , Hong Cai , Jisoo Jeong , Yinhao Zhu , Shizhong Han , Amin Ansari , Fatih Porikli

Learning-based 3D reconstruction using implicit neural representations has shown promising progress not only at the object level but also in more complicated scenes. In this paper, we propose Dynamic Plane Convolutional Occupancy Networks,…

Computer Vision and Pattern Recognition · Computer Science 2020-11-12 Stefan Lionar , Daniil Emtsev , Dusan Svilarkovic , Songyou Peng

In this paper, we explore a novel point representation for 3D occupancy prediction from multi-view images, which is named Occupancy as Set of Points. Existing camera-based methods tend to exploit dense volume-based representation to predict…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Yiang Shi , Tianheng Cheng , Qian Zhang , Wenyu Liu , Xinggang Wang

Autonomous driving requires robust perception across diverse environmental conditions, yet 3D semantic occupancy prediction remains challenging under adverse weather and lighting. In this work, we present the first study combining 4D radar…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 David Ninfa , Andras Palffy , Holger Caesar

Recently, implicit neural representations have gained popularity for learning-based 3D reconstruction. While demonstrating promising results, most implicit approaches are limited to comparably simple geometry of single objects and do not…

Computer Vision and Pattern Recognition · Computer Science 2020-08-04 Songyou Peng , Michael Niemeyer , Lars Mescheder , Marc Pollefeys , Andreas Geiger

Accurate 3D bird's-eye view (BEV) object detection is essential for autonomous driving, and depends strongly on effective multimodal representations from complementary sensors such as cameras and LiDAR. Multimodal masked autoencoders have…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Prabuddhi Wariyapperuma , Rajitha de Silva , Marc Hanheide , Thomas Bohné , Leonardo Guevara

Trajectory prediction in autonomous driving relies on accurate representation of all relevant contexts of the driving scene, including traffic participants, road topology, traffic signs, as well as their semantic relations to each other.…

Computer Vision and Pattern Recognition · Computer Science 2024-07-02 Zhigang Sun , Zixu Wang , Lavdim Halilaj , Juergen Luettin

Learning 3D scene geometry and semantics from images is a core challenge in computer vision and a key capability for autonomous driving. Since large-scale 3D annotation is prohibitively expensive, recent work explores self-supervised…

Computer Vision and Pattern Recognition · Computer Science 2025-11-24 Adam Lilja , Ji Lan , Junsheng Fu , Lars Hammarstrand

Vision-based Bird's Eye View (BEV) representation is an emerging perception formulation for autonomous driving. The core challenge is to construct BEV space with multi-camera features, which is a one-to-many ill-posed problem. Diving into…

Computer Vision and Pattern Recognition · Computer Science 2024-07-17 Yiming Wu , Ruixiang Li , Zequn Qin , Xinhai Zhao , Xi Li

Occupancy is crucial for autonomous driving, providing essential geometric priors for perception and planning. However, existing methods predominantly rely on LiDAR-based occupancy annotations, which limits scalability and prevents…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Baijun Ye , Minghui Qin , Saining Zhang , Moonjun Gong , Shaoting Zhu , Zebang Shen , Luan Zhang , Lu Zhang , Hao Zhao , Hang Zhao

Autonomous vehicles commonly rely on highly detailed birds-eye-view maps of their environment, which capture both static elements of the scene such as road layout as well as dynamic elements such as other cars and pedestrians. Generating…

Computer Vision and Pattern Recognition · Computer Science 2020-03-31 Thomas Roddick , Roberto Cipolla