A new benchmark for group distribution shifts in hand grasp regression for object manipulation. Can meta-learning raise the bar?

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.

October 2022 · Théo Morales, Gerard Lacey