KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypoints. (arXiv:2205.04992v2 [cs.CV] UPDATED)

Image-based volumetric humans using pixel-aligned features promise
generalization to unseen poses and identities. Prior work leverages global
spatial encodings and multi-view geometric consistency to reduce spatial
ambiguity. However, global encodings often suffer from overfitting to the
distribution of the training data, and it is difficult to learn multi-view
consistent reconstruction from sparse views. In this work, we investigate
common issues with existing spatial encodings and propose a simple yet highly
effective approach to modeling high-fidelity volumetric humans from sparse
views. …

arxiv avatars cv encoding image