Reproduce “DeTac: Dual-branch Decoupling of Texture and Force Signals in Vision-Based Tactile Sensors” 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
Zhirui Zhang, Yunkai Tang, Jiahang Li, Fan Fei, Jinnuo Zhang, Kairan Ding, Jieji Ren, Yandong Guo and 1 more
DeTac separates shading and marker signals from a mixed tactile image, generating a full marker-free shading image with diffusion while a lightweight network predicts markers. Two cross-branch losses emphasize shading near markers and align predicted markers with image changes. On held-out poses, it reaches PSNR 39.45 versus TacDiff’s 31.52, though training data differ; real-time use is unestablished.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.