Skip to content
Preprint

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

Nov 2026 · 0 citations · 63 references
Computer Science

TL;DR

ZARA is presented, a zero-shot feed-forward framework that reconstructs an animatable 3D Gaussian avatar together with its intrinsic attributes from a single image, outperforming existing baselines in both relighting quality and materials generalization ability.

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.

View source

Similar papers

Preprint Nov 2026

InstantHand: Feed-Forward 3D Gaussian Splatting for Animatable Hand Avatar Reconstruction from a Single Image

Hand avatar reconstruction typically relies on multi-view capture or per-subject optimization, limiting its scalability. We introduce InstantHand, a feed-forward framework that constructs an animatable 3D Gaussian hand avatar from a single image using off-the-shelf MANO, camera, and mask estimates, without test-time op...

Chanho Kim, M. Ali, Kyeonghwan Gwak et al. · 0 citations
Sep 2026

ARS-Avatar: Animatable and Relightable Surfel Avatars with Learnable Ambient Occlusion

ARS-Avatar is presented, a novel method using surfel representation for high-quality, animatable, and relightable human avatars from multi-view images captured under unknown illumination that achieves competitive or improved radiance reconstruction on multiple metrics and consistently outperforms the evaluated PBR reli...

Jia-Teng Liu, Hao Gao, Jun-Xin Sun et al. · 0 citations
Preprint Oct 2026

ManifoldSplat: Language-Guided Semantic Shape Editing of 3D Gaussian Head Avatars

High-fidelity 3D head avatars have reached near-photorealistic quality. While recent methods enable text-driven manipulation, they struggle to provide fine-grained localized control, often entangling features or lacking geometric consistency. Modifying geometry through natural language currently requires slow per-promp...

Antonio Canela, Jordi Sanchez-Riera · 0 citations
Preprint Oct 2026

MATE4D: Matrix-Guided Editable 4D Generation from a Single Image

Generative models have rapidly pushed content creation be-yond 2D imagery toward dynamic 3D and 4D scene synthesis. Yet pro-ducing realistic and temporally stable 4D content from a single image is still difficult because one view provides limited structural cues and weak motion evidence. We introduce MATE4D, a framewor...

Xiao-Tian Chen, Dong-Fu Yin · 0 citations
Preprint Oct 2026

SUPRA-TEX: 3D Generation with Super-Aligned Texture

Single image 3D generation aims to dress a given 3D mesh with relightable materials while faithfully preserving the visual details of a reference image. Existing methods either introduce artifacts when fusing inconsistent multi-view predictions or struggle to preserve fine details through implicit image-feature conditi...

Chen Yang, Jie-Min Fang, Fanpeng Meng et al. · 2 citations
Sep 2026

Relightable 3D Avatar Reconstruction with Semantic-Adaptive Motion-Illumination Responses

Reconstructing expressive and relightable 3D head avatars from monocular videos remains challenging in computer vision, as it requires accurate modeling of both non-rigid facial motion and illumination-dependent appearance. Existing Gaussian avatar methods commonly rely on globally coupled representations, in which Gau...

Jian-Kuo Zhao, Xiang-Yu Zhu, Ji-Jie Li et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.