Reproduce “DRHeC: Differentiable Rendering for Hand-Eye Calibration with RGB-Based Gradients” 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
Xiaotian Zhang, Yusheng Wang, Naoya Kagawa, Noritaka Takamura, Keiji Okuhara, Hiroyasu Baba, Jun Ota
DRHeC calibrates the transformation between a robot’s coordinate system and camera by comparing simulation-like RGB images with differentiably rendered robot images. It adds mask centroid and area cues to RGB loss and uses staged translation then rotation refinement. On UR5e, it reports 88.9% grasping and 57.4% insertion success, exceeding EasyHeC but below Single3D iterations, under stable indoor, eye-to-hand conditions.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.