Disentangling 3D Attributes from a Single 2D Image: Human Pose, Shape and Garment. (arXiv:2208.03167v1 [cs.CV])

For visual manipulation tasks, we aim to represent image content with
semantically meaningful features. However, learning implicit representations
from images often lacks interpretability, especially when attributes are
intertwined. We focus on the challenging task of extracting disentangled 3D
attributes only from 2D image data. Specifically, we focus on human appearance
and learn implicit pose, shape and garment representations of dressed humans
from RGB images. Our method learns an embedding with disentangled latent
representations of these three image properties and enables …

2d image 3d arxiv cv human image