Bringing Your Portrait to 3D Presence

TL;DR

This paper introduces a unified framework for creating animatable 3D human avatars from a single portrait, addressing pose sensitivity, data limitations, and proxy-mesh estimation issues.

Contribution

It proposes a Dual-UV representation and a synthetic data manifold, enabling robust in-the-wild 3D human avatar reconstruction from limited data.

Findings

Achieves state-of-the-art head and upper-body reconstruction.

Demonstrates strong generalization to in-the-wild images.

Provides competitive full-body reconstruction results.

Abstract

We present a unified framework for reconstructing animatable 3D human avatars from a single portrait across head, half-body, and full-body inputs. Our method tackles three bottlenecks: pose- and framing-sensitive feature representations, limited scalable data, and unreliable proxy-mesh estimation. We introduce a Dual-UV representation that maps image features to a canonical UV space via Core-UV and Shell-UV branches, eliminating pose- and framing-induced token shifts. We also build a factorized synthetic data manifold combining 2D generative diversity with geometry-consistent 3D renderings, supported by a training scheme that improves realism and identity consistency. A robust proxy-mesh tracker maintains stability under partial visibility. Together, these components enable strong in-the-wild generalization. Trained only on half-body synthetic data, our model achieves state-of-the-art head and upper-body reconstruction and competitive full-body results. Extensive experiments and analyses further validate the effectiveness of our approach.