occlusions
Obstructions that prevent the full visibility of objects in visual data, posing challenges for computer vision models that must accurately recognize or reconstruct scenes.
- AGC-Drive: A Large-Scale Dataset for Real-World Aerial-Ground Collaboration in Driving Scenarios
- GSAlign: Geometric and Semantic Alignment Network for Aerial-Ground Person Re-Identification
- Restage4D: Reanimating Deformable 3D Reconstruction from a Single Video
- STAR: Spatial-Temporal Tracklet Matching for Multi-Object Tracking
- SegMASt3R: Geometry Grounded Segment Matching
- UrbanIng-V2X: A Large-Scale Multi-Vehicle, Multi-Infrastructure Dataset Across Multiple Intersections for Cooperative Perception
- V2X-Radar: A Multi-modal Dataset with 4D Radar for Cooperative Perception
- VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment