Capture, Canonicalize, Splat: Zero-Shot 3D Gaussian Avatars from Unstructured Phone Images

• URL: http://arxiv.org/abs/2510.14081v3
• Date: Mon, 27 Oct 2025 13:30:00 GMT
• Title: Capture, Canonicalize, Splat: Zero-Shot 3D Gaussian Avatars from Unstructured Phone Images
• Abstract summary: "Capture, Canonicalize, Splat" pipeline produces static quarter-body avatars with compelling realism and robust identity preservation from unstructured photos.<n>This "Capture, Canonicalize, Splat" pipeline produces static quarter-body avatars with compelling realism and robust identity preservation from unstructured photos.
• Score: 20.85870756824163
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a novel, zero-shot pipeline for creating hyperrealistic, identity-preserving 3D avatars from a few unstructured phone images. Existing methods face several challenges: single-view approaches suffer from geometric inconsistencies and hallucinations, degrading identity preservation, while models trained on synthetic data fail to capture high-frequency details like skin wrinkles and fine hair, limiting realism. Our method introduces two key contributions: (1) a generative canonicalization module that processes multiple unstructured views into a standardized, consistent representation, and (2) a transformer-based model trained on a new, large-scale dataset of high-fidelity Gaussian splatting avatars derived from dome captures of real people. This "Capture, Canonicalize, Splat" pipeline produces static quarter-body avatars with compelling realism and robust identity preservation from unstructured photos.

Related papers

• HumanNOVA: Photorealistic, Universal and Rapid 3D Human Avatar Modeling from a Single Image [84.81016200801153]
  We present HumanNOVA, a photorealistic, universal, and rapid model for generating 3D human avatars from a single RGB image.<n>In terms of the architecture, HumanNOVA adopts a feed-forward, token-conditioned avatar modeling framework that allows fast inference in less than one second.
  arXiv  Detail & Related papers  (2026-06-01T17:58:11Z)
• Splatshot: 3D Face Avatar Generation from a Single Unconstrained Photo [22.10478800887373]
  We present SplatShot, a training-free framework that couples explicit 3D representations directly within the denoising process.<n>Experiments on diverse in-the-wild images demonstrate that SplatShot produces 3D avatars with superior identity preservation, photorealism, and multi-view consistency.
  arXiv  Detail & Related papers  (2026-05-31T23:19:44Z)
• Structure-Aware Fine-Grained Gaussian Splatting for Expressive Avatar Reconstruction [27.915439949805876]
  We propose a novel method for reconstructing expressive and coherent full-body 3D human avatars from a monocular video sequence.<n>Our method requires only a single-stage training and outperforms state-of-the-art baselines in both quantitative and qualitative evaluations.
  arXiv  Detail & Related papers  (2026-04-10T13:49:15Z)
• DipGuava: Disentangling Personalized Gaussian Features for 3D Head Avatars from Monocular Video [56.39805581764342]
  DipGuava is a novel 3D Gaussian head avatar creation method that generates avatars with personalized attributes from monocular video.<n>It is the first method to explicitly disentangle facial appearance into two complementary components, trained in a structured two-stage pipeline.<n>It consistently outperforms prior methods in both visual quality and quantitativeperformance, as demonstrated in extensive experiments.
  arXiv  Detail & Related papers  (2026-03-30T03:50:23Z)
• OMEGA-Avatar: One-shot Modeling of 360° Gaussian Avatars [54.688420347927725]
  OMEGA-Avatar is the first framework that simultaneously generates a generalizable, 360-complete, and animatable 3D Gaussian head from a single image.<n>We show that OMEGA-Avatar achieves state-of-the-art performance, significantly outperforming existing baselines in 360 full-head completeness.
  arXiv  Detail & Related papers  (2026-02-12T08:16:38Z)
• 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)
• MoGA: 3D Generative Avatar Prior for Monocular Gaussian Avatar Reconstruction [65.5412504339528]
  MoGA is a novel method to reconstruct high-fidelity 3D Gaussian avatars from a single-view image.<n>Our method surpasses state-of-the-art techniques and generalizes well to real-world scenarios.
  arXiv  Detail & Related papers  (2025-07-31T14:36:24Z)
• SEGA: Drivable 3D Gaussian Head Avatar from a Single Image [15.117619290414064]
  We propose SEGA, a novel approach for 3D drivable Gaussian head Avatar creation.<n>SEGA seamlessly combines priors derived from large-scale 2D datasets with 3D priors learned from multi-view, multi-expression, and multi-ID data.<n>Experiments show our method outperforms state-of-the-art approaches in generalization ability, identity preservation, and expression realism.
  arXiv  Detail & Related papers  (2025-04-19T18:23:31Z)
• FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images [74.86864398919467]
  We present a novel method for reconstructing personalized 3D human avatars with realistic animation from only a few images.<n>We learn a universal prior from over a thousand clothed humans to achieve instant feedforward generation and zero-shot generalization.<n>Our method generates more authentic reconstruction and animation than state-of-the-arts, and can be directly generalized to inputs from casually taken phone photos.
  arXiv  Detail & Related papers  (2025-03-24T23:20:47Z)
• Synthetic Prior for Few-Shot Drivable Head Avatar Inversion [61.51887011274453]
  We present SynShot, a novel method for the few-shot inversion of a drivable head avatar based on a synthetic prior.<n>Inspired by machine learning models trained solely on synthetic data, we propose a method that learns a prior model from a large dataset of synthetic heads.
  arXiv  Detail & Related papers  (2025-01-12T19:01:05Z)
• Deformable 3D Gaussian Splatting for Animatable Human Avatars [50.61374254699761]
  We propose a fully explicit approach to construct a digital avatar from as little as a single monocular sequence. ParDy-Human constitutes an explicit model for realistic dynamic human avatars which requires significantly fewer training views and images. Our avatars learning is free of additional annotations such as Splat masks and can be trained with variable backgrounds while inferring full-resolution images efficiently even on consumer hardware.
  arXiv  Detail & Related papers  (2023-12-22T20:56:46Z)
• Generalizable One-shot Neural Head Avatar [90.50492165284724]
  We present a method that reconstructs and animates a 3D head avatar from a single-view portrait image. We propose a framework that not only generalizes to unseen identities based on a single-view image, but also captures characteristic details within and beyond the face area.
  arXiv  Detail & Related papers  (2023-06-14T22:33:09Z)
• PVA: Pixel-aligned Volumetric Avatars [34.929560973779466]
  We devise a novel approach for predicting volumetric avatars of the human head given just a small number of inputs. Our approach is trained in an end-to-end manner solely based on a photometric re-rendering loss without requiring explicit 3D supervision.
  arXiv  Detail & Related papers  (2021-01-07T18:58:46Z)

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.