HandTailor: Towards High-Precision Monocular 3D Hand Recovery
This work addresses high-precision 3D hand recovery for computer vision applications, representing an incremental improvement over existing methods.
The authors tackled 3D hand pose and shape recovery from a single RGB image by introducing HandTailor, a framework combining a learning-based hand module and an optimization-based tailor module, achieving state-of-the-art performance on public benchmarks with the tailor module running at 8ms per frame on a CPU.
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 unifies 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, and iteratively optimizes an energy function 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 on in-the-wild experiments. Code and video are available on our project webpage https://sites.google.com/view/handtailor.