6 papers
VGGT-Segmentor: Geometry-Enhanced Cross-View Segmentation
Yulu Gao, Bohao Zhang, Zongheng Tang +3
Instance-level object segmentation across disparate egocentric and exocentric views is a fundamental challenge in visual understanding, critical for applications in embodied AI and…
Unified Modeling of Lane and Lane Topology for Driving Scene Reasoning
Han Li, Yulu Gao, Si Liu +3
Autonomous vehicles need to perceive not only physical elements in the driving scene, such as lane lines and traffic lights, but also logical elements like lane centerlines and the…
RATopo: Improving Lane Topology Reasoning via Redundancy Assignment
Han Li, Shaofei Huang, Longfei Xu +3
Lane topology reasoning plays a critical role in autonomous driving by modeling the connections among lanes and the topological relationships between lanes and traffic elements. Mo…
DOMR: Establishing Cross-View Segmentation via Dense Object Matching
Jitong Liao, Yulu Gao, Shaofei Huang +4
Cross-view object correspondence involves matching objects between egocentric (first-person) and exocentric (third-person) views. It is a critical yet challenging task for visual u…
CoST: Efficient Collaborative Perception From Unified Spatiotemporal Perspective
Zongheng Tang, Yi Liu, Yifan Sun +4
Collaborative perception shares information among different agents and helps solving problems that individual agents may face, e.g., occlusions and small sensing range. Prior metho…
MV2DFusion: Leveraging Modality-Specific Object Semantics for Multi-Modal 3D Detection
Zitian Wang, Zehao Huang, Yulu Gao +2
The rise of autonomous vehicles has significantly increased the demand for robust 3D object detection systems. While cameras and LiDAR sensors each offer unique advantages--cameras…