Related papers: PointOBB-v3: Expanding Performance Boundaries of S…

In autonomous driving, 3D object detection based on multi-modal data has become an indispensable approach when facing complex environments around the vehicle. During multi-modal detection, LiDAR and camera are simultaneously applied for…

This work presents Orient Anything V2, an enhanced foundation model for unified understanding of object 3D orientation and rotation from single or paired images. Building upon Orient Anything V1, which defines orientation via a single…

We present an endpoint box regression module(epBRM), which is designed for predicting precise 3D bounding boxes using raw LiDAR 3D point clouds. The proposed epBRM is built with sequence of small networks and is computationally lightweight.…

Monocular omnidirectional visual odometry (OVO) systems leverage 360-degree cameras to overcome field-of-view limitations of perspective VO systems. However, existing methods, reliant on handcrafted features or photometric objectives, often…

Robust 3D occupancy prediction is essential for autonomous driving, particularly under adverse weather conditions where traditional vision-only systems struggle. While the fusion of surround-view 4D radar and cameras offers a promising…

Current 3D single object tracking approaches track the target based on a feature comparison between the target template and the search area. However, due to the common occlusion in LiDAR scans, it is non-trivial to conduct accurate feature…

Traditional semi-supervised object detection methods assume a fixed set of object classes (in-distribution or ID classes) during training and deployment, which limits performance in real-world scenarios where unseen classes…

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,…

3D single object tracking (SOT) is an indispensable part of automated driving. Existing approaches rely heavily on large, densely labeled datasets. However, annotating point clouds is both costly and time-consuming. Inspired by the great…

Unsupervised 3D object detection leverages heuristic algorithms to discover potential objects, offering a promising route to reduce annotation costs in autonomous driving. Existing approaches mainly generate pseudo labels and refine them…

Semi-supervised 3D object detection (SS3DOD) aims to reduce costly 3D annotations utilizing unlabeled data. Recent studies adopt pseudo-label-based teacher-student frameworks and demonstrate impressive performance. The main challenge of…

3D object detection is a common function within the perception system of an autonomous vehicle and outputs a list of 3D bounding boxes around objects of interest. Various 3D object detection methods have relied on fusion of different sensor…

Learning model-free object pose estimation for unseen instances remains a fundamental challenge in 3D vision. Existing methods typically fall into two disjoint paradigms: category-level approaches predict absolute poses in a canonical space…

Manual annotation of large-scale point cloud dataset for varying tasks such as 3D object classification, segmentation and detection is often laborious owing to the irregular structure of point clouds. Self-supervised learning, which…

With the emergence of transformer-based architectures and large language models (LLMs), the accuracy of road scene perception has substantially advanced. Nonetheless, current road scene segmentation approaches are predominantly trained on…

Collaborative perception allows agents to enhance their perceptual capabilities by exchanging intermediate features. Existing methods typically organize these intermediate features as 2D bird's-eye-view (BEV) representations, which discard…

Object-centric scene understanding is a fundamental challenge in computer vision. Existing approaches often rely on multi-stage pipelines that first apply pre-trained segmentors to extract individual objects, followed by per-object 3D…

Multi-sensor fusion significantly enhances the accuracy and robustness of 3D semantic occupancy prediction, which is crucial for autonomous driving and robotics. However, most existing approaches depend on high-resolution images and complex…

Oriented object detection emerges in many applications from aerial images to autonomous driving, while many existing detection benchmarks are annotated with horizontal bounding box only which is also less costive than fine-grained rotated…

In this paper, we propose PASS3D to achieve point-wise semantic segmentation for 3D point cloud. Our framework combines the efficiency of traditional geometric methods with robustness of deep learning methods, consisting of two stages: At…