Related papers: PointOcc: Cylindrical Tri-Perspective View for Poi…
In contrast to extensive studies on general vision, pre-training for scalable visual autonomous driving remains seldom explored. Visual autonomous driving applications require features encompassing semantics, 3D geometry, and temporal…
In this paper, we introduce ProtoOcc, a novel 3D occupancy prediction model designed to predict the occupancy states and semantic classes of 3D voxels through a deep semantic understanding of scenes. ProtoOcc consists of two main…
Exploiting past 3D LiDAR scans to predict future point clouds is a promising method for autonomous mobile systems to realize foresighted state estimation, collision avoidance, and planning. In this paper, we address the problem of…
The task of estimating 3D occupancy from surrounding-view images is an exciting development in the field of autonomous driving, following the success of Bird's Eye View (BEV) perception. This task provides crucial 3D attributes of the…
In this technical report, we present our solution for the Vision-Centric 3D Occupancy and Flow Prediction track in the nuScenes Open-Occ Dataset Challenge at CVPR 2024. Our innovative approach involves a dual-stage framework that enhances…
Point cloud has been widely used in the field of autonomous driving since it can provide a more comprehensive three-dimensional representation of the environment than 2D images. Point-wise prediction based on point cloud sequence (PCS) is…
Image-only and pseudo-LiDAR representations are commonly used for monocular 3D object detection. However, methods based on them have shortcomings of either not well capturing the spatial relationships in neighbored image pixels or being…
Panoramic imagery provides holistic 360{\deg} visual coverage for perception in quadruped robots. However, existing occupancy prediction methods are mainly designed for wheeled autonomous driving and rely heavily on RGB cues, limiting their…
3D semantic occupancy prediction is crucial for finely representing the surrounding environment, which is essential for ensuring the safety in autonomous driving. Existing fusion-based occupancy methods typically involve performing a…
In this paper, we study the problem of 3D object segmentation from raw point clouds. Unlike all existing methods which usually require a large amount of human annotations for full supervision, we propose the first unsupervised method,…
Collaborative perception in automated vehicles leverages the exchange of information between agents, aiming to elevate perception results. Previous camera-based collaborative 3D perception methods typically employ 3D bounding boxes or…
The capability for open vocabulary perception represents a significant advancement in autonomous driving systems, facilitating the comprehension and interpretation of a wide array of textual inputs in real-time. Despite extensive research…
LiDAR point clouds can effectively depict the motion and posture of objects in three-dimensional space. Many studies accomplish the 3D object detection by voxelizing point clouds. However, in autonomous driving scenarios, the sparsity and…
Semantic segmentation of point clouds usually requires exhausting efforts of human annotations, hence it attracts wide attention to the challenging topic of learning from unlabeled or weaker forms of annotations. In this paper, we take the…
With the growing demand for oriented object detection (OOD), recent studies on point-supervised OOD have attracted significant interest. In this paper, we propose PointOBB-v3, a stronger single point-supervised OOD framework. Compared to…
Autonomous vehicles need a complete map of their surroundings to plan and act. This has sparked research into the tasks of 3D occupancy prediction, 3D scene completion, and 3D panoptic scene completion, which predict a dense map of the ego…
Three dimensional (3D) object recognition is becoming a key desired capability for many computer vision systems such as autonomous vehicles, service robots and surveillance drones to operate more effectively in unstructured environments.…
Comprehensive and consistent dynamic scene understanding from camera input is essential for advanced autonomous systems. Traditional camera-based perception tasks like 3D object tracking and semantic occupancy prediction lack either spatial…
Addressing the task of 3D semantic occupancy prediction for autonomous driving, we tackle two key issues in existing 3D Gaussian Splatting (3DGS) methods: (1) unified feature aggregation neglecting semantic correlations among similar…
3D occupancy prediction enables the robots to obtain spatial fine-grained geometry and semantics of the surrounding scene, and has become an essential task for embodied perception. Existing methods based on 3D Gaussians instead of dense…