4 papers
GradSplat: Gradients Inside the Forward Pass for Feed-Forward 3D Gaussian Splatting
Jingong Chen, Linlian Jiang, Guangyuan Li +5
Feed-forward 3D Gaussian Splatting predicts a scene from a few images, but our predictor is less accurate than its own Gaussians optimized per scene on those images. This gap lies…
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…
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…
SAGOnline: Segment Any Gaussians Online
Wentao Sun, Quanyun Wu, Hanqing Xu +7
3D Gaussian Splatting has emerged as a powerful paradigm for explicit 3D scene representation, yet achieving efficient and consistent 3D segmentation remains challenging. Existing…