2 papers
cs.CV2024
Diverse 3D Human Pose Generation in Scenes based on Decoupled Structure
Bowen Dang, Xi Zhao
This paper presents a novel method for generating diverse 3D human poses in scenes with semantic control. Existing methods heavily rely on the human-scene interaction dataset, resu…
cs.CV2023
Reconstructing 3D Human Pose from RGB-D Data with Occlusions
Bowen Dang, Xi Zhao, Bowen Zhang +1
We propose a new method to reconstruct the 3D human body from RGB-D images with occlusions. The foremost challenge is the incompleteness of the RGB-D data due to occlusions between…