papers AI Learner
The Github is limit! Click to go to the new site.

Patch-based 3D Human Pose Refinement

2019-05-20
Qingfu Wan, Weichao Qiu, Alan L. Yuille

Abstract

State-of-the-art 3D human pose estimation approaches typically estimate pose from the entire RGB image in a single forward run. In this paper, we develop a post-processing step to refine 3D human pose estimation from body part patches. Using local patches as input has two advantages. First, the fine details around body parts are zoomed in to high resolution for preciser 3D pose prediction. Second, it enables the part appearance to be shared between poses to benefit rare poses. In order to acquire informative representation of patches, we explore different input modalities and validate the superiority of fusing predicted segmentation with RGB. We show that our method consistently boosts the accuracy of state-of-the-art 3D human pose methods.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.08231

PDF

http://arxiv.org/pdf/1905.08231


Similar Posts

Comments