Reproduce “GelSlim 5.0: Unifying Vision and Touch with a Single Fingertip Camera” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Xiangdong Wang, I-Hsuan Huang, Xiaohao Xu, Xili Yi, Nima Fazeli, Xiaonan Huang
VisTacFusion combines sequential visual and tactile views from one fixed fingertip camera to estimate planar object pose and local contact geometry. UV illumination switches between views, and visual context informs separate pose and depth-and-normal predictions. On 12 known objects, paired inputs reduce depth MSE from 0.0170 to 0.0066 mm². Validation is within-session, with computed geometry references.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.