We present an unsupervised incremental learning method for refining hand shape and pose estimation. We propose a refiner network (RefNet) that can augment a state-of-the-art hand tracking system (BaseNet) by refining its estimations on unlabeled data. At each input depth frame, the estimations from the BaseNet are iteratively refined by RefNet using a model-fitting strategy. During this process, the RefNet adapts to the input data characteristics by incremental learning. We show that our method provides more accurate hand shape and pose estimates on both a standard dataset and real data.
This work won the third place in the ACM Student Research Competition (SRC) at SIGGRAPH 2019.