Bringing Your Portrait to 3D Presence
This addresses the challenge of creating realistic 3D avatars from limited 2D inputs for applications in virtual reality, gaming, and digital media, representing a novel method for known bottlenecks.
The paper tackles the problem of reconstructing animatable 3D human avatars from a single portrait across head, half-body, and full-body inputs, achieving state-of-the-art head and upper-body reconstruction and competitive full-body results.
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.