RGB-Dデータによる頑健な人体メッシュ復元
Towards Robust RGB-D Human Mesh Recovery
RGBのみでは3D姿勢が不定になりやすい問題に対し、RGBとRGB-Dデータを組み合わせて学習する動的融合モジュールやSMPL監督信号の生成、深度順位学習を導入し、パラメトリック人体メッシュを推定する手法を提案した。
著者: Ren Li, Changjiang Cai, Georgios Georgakis, Srikrishna Karanam, Terrence Chen, Ziyan Wu
分類: cs.CV, cs.LG, cs.RO
原文アブストラクト
We consider the problem of human pose estimation. While much recent work has focused on the RGB domain, these techniques are inherently under-constrained since there can be many 3D configurations that explain the same 2D projection. To this end, we propose a new method that uses RGB-D data to estimate a parametric human mesh model. Our key innovations include (a) the design of a new dynamic data fusion module that facilitates learning with a combination of RGB-only and RGB-D datasets, (b) a new constraint generator module that provides SMPL supervisory signals when explicit SMPL annotations are not available, and (c) the design of a new depth ranking learning objective, all of which enable principled model training with RGB-D data. We conduct extensive experiments on a variety of RGB-D datasets to demonstrate efficacy.
