Revisiting Avatar-As-Image: High-Fidelity Registration is All You Need

• URL: http://arxiv.org/abs/2609.11722v1
• Date: Thu, 10 Sep 2026 15:40:39 GMT
• Title: Revisiting Avatar-As-Image: High-Fidelity Registration is All You Need
• Abstract summary: AvaImg outperforms all baselines in body fitting, shape estimation, and surface registration across six datasets.<n>For validation of AvaImg's Avatar-as-Image representation we auto-encode our UV maps via the frozen FLUX VAE.
• Score: 25.222133417690852
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The representation of 3D clothed humans as standardized 2D UV texture and displacement maps over an underlying body model has long been studied. This compact representation is enticing as it enables pretrained image networks to process, generate, and edit 3D avatars, but is only useful if scans are accurately aligned and brought into correspondence via high-fidelity registration. This prerequisite has never been met, which we argue explains the limited quality of prior UV-based methods for clothed humans. Despite its significance, no public method produces high-fidelity SMPL(-X)+D registrations with UV texture from arbitrary clothed scans. We present AvaImg, a multi-stage optimization pipeline, to close this gap: it enforces body-inside-clothing constraint via signed winding numbers, made viable by a three-level efficiency cascade (~10x runtime reduced, ~95% storage saved), and recovers fine surface detail using coarse-to-fine displacement optimization. AvaImg outperforms all baselines in body fitting, shape estimation, and surface registration across six datasets, yielding textured registrations near-indistinguishable from scans (PSNR=34.48dB). For validation of AvaImg's Avatar-as-Image representation as imminently compatible with image foundation models, we auto-encode our UV maps via the frozen FLUX VAE. This achieves only 0.76mm added Chamfer error relative to scan and shows that the resulting maps lie within natural-image distributions, supporting the use of 2D generative priors for 3D avatar generation. Code, data, and Singularity containers will be at https://yuxuan-xue.com/avaimg.

Related papers

• PFAvatar: Pose-Fusion 3D Personalized Avatar Reconstruction from Real-World Outfit-of-the-Day Photos [24.8968050268664]
  PFAvatar is a new method that reconstructs high-quality 3D avatars from Outfit of the Day (OOTD) photos.<n>Our method completes personalization in just 5 minutes, achieving a 48x speed-up compared to previous approaches.
  arXiv  Detail & Related papers  (2025-11-17T03:40:43Z)
• FAMOUS: High-Fidelity Monocular 3D Human Digitization Using View Synthesis [51.193297565630886]
  The challenge of accurately inferring texture remains, particularly in obscured areas such as the back of a person in frontal-view images. This limitation in texture prediction largely stems from the scarcity of large-scale and diverse 3D datasets. We propose leveraging extensive 2D fashion datasets to enhance both texture and shape prediction in 3D human digitization.
  arXiv  Detail & Related papers  (2024-10-13T01:25:05Z)
• UVMap-ID: A Controllable and Personalized UV Map Generative Model [67.71022515856653]
  We introduce UVMap-ID, a controllable and personalized UV Map generative model. Unlike traditional large-scale training methods in 2D, we propose to fine-tune a pre-trained text-to-image diffusion model. Both quantitative and qualitative analyses demonstrate the effectiveness of our method in controllable and personalized UV Map generation.
  arXiv  Detail & Related papers  (2024-04-22T20:30:45Z)
• UV Gaussians: Joint Learning of Mesh Deformation and Gaussian Textures for Human Avatar Modeling [71.87807614875497]
  We propose UV Gaussians, which models the 3D human body by jointly learning mesh deformations and 2D UV-space Gaussian textures. We collect and process a new dataset of human motion, which includes multi-view images, scanned models, parametric model registration, and corresponding texture maps. Experimental results demonstrate that our method achieves state-of-the-art synthesis of novel view and novel pose.
  arXiv  Detail & Related papers  (2024-03-18T09:03:56Z)
• Chupa: Carving 3D Clothed Humans from Skinned Shape Priors using 2D Diffusion Probabilistic Models [9.479195068754507]
  We propose a 3D generation pipeline that uses diffusion models to generate realistic human digital avatars. Our method, namely, Chupa, is capable of generating realistic 3D clothed humans with better perceptual quality and identity variety.
  arXiv  Detail & Related papers  (2023-05-19T17:59:18Z)
• DRaCoN -- Differentiable Rasterization Conditioned Neural Radiance Fields for Articulated Avatars [92.37436369781692]
  We present DRaCoN, a framework for learning full-body volumetric avatars. It exploits the advantages of both the 2D and 3D neural rendering techniques. Experiments on the challenging ZJU-MoCap and Human3.6M datasets indicate that DRaCoN outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-03-29T17:59:15Z)
• AGORA: Avatars in Geography Optimized for Regression Analysis [35.22486186509372]
  AGORA is a synthetic dataset with high realism and highly accurate ground truth. We create reference 3D poses and body shapes by fitting the SMPL-X body model (with face and hands) to the 3D scans. We evaluate existing state-of-the-art methods for 3D human pose estimation on this dataset and find that most methods perform poorly on images of children.
  arXiv  Detail & Related papers  (2021-04-29T20:33:25Z)
• OSTeC: One-Shot Texture Completion [86.23018402732748]
  We propose an unsupervised approach for one-shot 3D facial texture completion. The proposed approach rotates an input image in 3D and fill-in the unseen regions by reconstructing the rotated image in a 2D face generator. We frontalize the target image by projecting the completed texture into the generator.
  arXiv  Detail & Related papers  (2020-12-30T23:53:26Z)
• 3D Human Mesh Regression with Dense Correspondence [95.92326689172877]
  Estimating 3D mesh of the human body from a single 2D image is an important task with many applications such as augmented reality and Human-Robot interaction. Prior works reconstructed 3D mesh from global image feature extracted by using convolutional neural network (CNN), where the dense correspondences between the mesh surface and the image pixels are missing. This paper proposes a model-free 3D human mesh estimation framework, named DecoMR, which explicitly establishes the dense correspondence between the mesh and the local image features in the UV space.
  arXiv  Detail & Related papers  (2020-06-10T08:50:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.