Abstract:
3D hand pose estimation and shape recovery are challenging tasks in computer vision. We introduce a novel framework HandTailor, which combines a learning-based hand module and an optimization-based tailor module to achieve high-precision hand mesh recovery from a monocular RGB image. The proposed hand module adapts both perspective projection and weak perspective projection in a single network towards accuracy-oriented and in-the-wild scenarios. The proposed tailor module then utilizes the coarsely reconstructed mesh model provided by the hand module as initialization to obtain better results. The tailor module is time-efficient, costs only ~8ms per frame on a modern CPU. We demonstrate that HandTailor can get state-of-the-art performance on several public benchmarks, with impressive qualitative results. Code and video are available on our project webpage https://sites.google.com/view/handtailor.
