2 papers
cs.CV2026
When Wider Views Fail: Stress-Testing Feed-Forward 3D Reconstruction
Daisy Li, Kyle Gao, Quanyun Wu +3
Feed-forward 3D reconstruction models enable efficient geometry estimation from sparse images, but their pretrained nature can make them vulnerable to distribution shifts beyond th…
cs.CV2026
ZVeC: A Zero-Shot Framework for Instance-Level Vehicle Extraction and Generative Point Cloud Completion
Daisy Li, Kyle Gao, Quanyun Wu +3
LiDAR point clouds acquired in underground environments exhibit severe geometric incompleteness due to occlusions and limited sensor viewpoints, making reliable point cloud complet…