A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf
.
KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypoints
[article]
2022
arXiv
pre-print
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
arXiv:2205.04992v2
fatcat:l756lhnexjh2pdb22aspwvc3bi