cs.CVNov 7, 2026

ZARA: Zero-shot Animatable and Relightable 3D Avatar reconstruction from a single image

Authors: Yixiao Chen, Dongdong Weng, Chengfeng Zhao, Tao Gong, Zhihe Zhao, Zhe Zhu, Yue Liu, Yuan Liu

Abstract

Recent large human reconstruction models create remarkable animatable 3D avatars from a single image, but their appearance remains entangled with the illumination and cannot be relighted. In contrast, existing 3D relightable-avatar reconstruction methods typically require person-specific optimization. We present ZARA, a zero-shot feed-forward framework that reconstructs an animatable 3D Gaussian avatar together with its intrinsic attributes from a single image. ZARA couples a pretrained large-scale human reconstruction model with a Material Transformer to inherit geometry priors while learning material-aware Gaussian representations. To preserve localized details, we introduce Gaussian-aligned material feature fusion strategy, which injects multi-scale material features onto individual Gaussians and combines them with geometry tokens. As most human-avatar datasets lack ground-truth material maps, we use pseudo-material labels as conditioning inputs and supervision targets during training. We further introduce MatFace regularization to preserve facial structure and color in albedo prediction under unreliable facial pseudo-material supervision. Extensive experiments demonstrate that ZARA reconstructs animatable and relightable humans within tens of seconds without person-specific optimization or post-processing, outperforming existing baselines in both relighting quality and materials generalization ability. As the ability of recovering the physically-based-rendering attributes of the human, ZARA also enables direct material editing of the avatar's appearance.

Figures & tables

Explore similar work

CardsList
  1. FFAvatar: Few-Shot, Feed-Forward, and Generalizable Avatar Reconstruction

    May 14, 2026Thuan Hoang Nguyen, Jiahao Luo, Yinyu Nie +33D Gaussian Splatting3D Reconstruction

  2. ARG-Avatar: Animation-Rendering Guidance for Efficient Feedforward Avatar Reconstruction

    Nov 17, 2026Jianjin Xu, Soham Dasgupta, Fernando De la Torre3D Human Reconstruction3D Avatar Generation

  3. Forwardrobe: Garment-Aware Gaussian Avatars from a Single Image

    Jul 31, 2026Daisheng Jin, Shuyun Wang, Ying He3D Gaussian Splatting3D Reconstruction