Yebin Liu (刘烨斌)
Zhe Li (李哲)'s Homepage
Description: A one-stage whole-body mesh recovery method OSX and an upper-body dataset UBody.
nerf (138) d-nerf (47) nerfies (46)
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 texture vocabulary for encoding dynamic human appearances under various poses. Unlike the commonly used joint-wise manner, we further design a body-part-wise encoding strategy to learn the structural effects of the kinematic chain.
Given a driving pose, we query the pose feature hierarchically by decomposing the pose vector into several body parts and interpolating the texture features for synthesizing fine-grained human dynamics.
Yebin Liu (刘烨斌)
Zhe Li (李哲)'s Homepage