HandTailor: Towards High-Precision Monocular 3D Hand Recovery

Autor:	Lv, Jun, Xu, Wenqiang, Yang, Lixin, Qian, Sucheng, Mao, Chongzhao, Lu, Cewu
Rok vydání:	2021
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	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. Comment: BMVC2021
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2102.09244 Zobrazit plný text záznamu View this record from Arxiv