grasping

We present a Coarse Hand-Object Interaction Representation (CHOIR), a novel, versatile and fully differentiable field for HOI modelling. CHOIR leverages discrete unsigned distances for continuous shape and pose encoding, alongside multivariate Gaussian distributions to represent dense contact maps with few parameters.

Computer vision in hand-object pose has diverse applications. Current methods on balanced datasets may not perform well in real-world scenarios. We introduce a benchmark for handling pose distribution shifts and propose meta-learning for adaptation. Results improve over the baseline, but face optimization challenges. Our analysis guides future benchmark work.