Preprint
Aug 2026
VisTa3D: A Dataset and Benchmark for Thin Object Reconstruction from Vision, Tactile, and 3D Point Clouds
State-of-the-art 3D reconstruction models, whether from visual, range, or both, tend to underperform on thin objects. This is partially due to the small amount of space such objects occupy in RGB images and in 3D point clouds. To test the extent of their errors, we collected the first thin object dataset comprising of...
Shania Guo, Yeongsik Seo, Andrew Fu et al.
· 1 citation