NoPo-Avatar: Generalizable and Animatable Avatars from Sparse Inputs without Human Poses

TL;DR

NoPo-Avatar is a novel method for creating animatable 3D human avatars from sparse images without relying on human pose inputs, making it robust to pose estimation noise and broadly applicable.

Contribution

It introduces a pose-free reconstruction approach that outperforms pose-dependent methods in noisy conditions and matches their performance in ideal settings.

Findings

Outperforms existing methods without pose inputs on challenging datasets

Robust to noisy human pose estimates

Achieves comparable results to pose-dependent methods in controlled settings

Abstract

We tackle the task of recovering an animatable 3D human avatar from a single or a sparse set of images. For this task, beyond a set of images, many prior state-of-the-art methods use accurate "ground-truth" camera poses and human poses as input to guide reconstruction at test-time. We show that pose-dependent reconstruction degrades results significantly if pose estimates are noisy. To overcome this, we introduce NoPo-Avatar, which reconstructs avatars solely from images, without any pose input. By removing the dependence of test-time reconstruction on human poses, NoPo-Avatar is not affected by noisy human pose estimates, making it more widely applicable. Experiments on challenging THuman2.0, XHuman, and HuGe100K data show that NoPo-Avatar outperforms existing baselines in practical settings (without ground-truth poses) and delivers comparable results in lab settings (with ground-truth poses).