TexVocab: Texture Vocabulary-conditioned Human Avatars

arXiv:2404.00524v1 Announce Type: new
Abstract: To adequately utilize the available image evidence in multi-view video-based avatar modeling, we propose TexVocab, a novel avatar representation that constructs a texture vocabulary and associates body poses with texture maps for animation. Given multi-view RGB videos, our method initially back-projects all the available images in the training videos to the posed SMPL surface, producing texture maps in the SMPL UV domain. Then we construct pairs of human poses and texture maps to establish a …

arxiv avatars cs.cv human texture type