NoPo-Avatar: Generalizable and Animatable Avatars from Sparse Inputs without Human Poses

• URL: http://arxiv.org/abs/2511.16673v1
• Date: Thu, 20 Nov 2025 18:59:54 GMT
• Title: NoPo-Avatar: Generalizable and Animatable Avatars from Sparse Inputs without Human Poses
• Authors: Jing Wen, Alexander G. Schwing, Shenlong Wang,
• Abstract summary: We tackle the task of recovering an animatable 3D human avatar from a single or a sparse set of images.<n>We show that pose-dependent reconstruction degrades results significantly if pose estimates are noisy.<n>We introduce NoPo-Avatar, which reconstructs avatars solely from images, without any pose input.
• Score: 94.67451270421323
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We tackle the task of recovering an animatable 3D human avatar from a single or a sparse set of images. For this task, beyond a set of images, many prior state-of-the-art methods use accurate "ground-truth" camera poses and human poses as input to guide reconstruction at test-time. We show that pose-dependent reconstruction degrades results significantly if pose estimates are noisy. To overcome this, we introduce NoPo-Avatar, which reconstructs avatars solely from images, without any pose input. By removing the dependence of test-time reconstruction on human poses, NoPo-Avatar is not affected by noisy human pose estimates, making it more widely applicable. Experiments on challenging THuman2.0, XHuman, and HuGe100K data show that NoPo-Avatar outperforms existing baselines in practical settings (without ground-truth poses) and delivers comparable results in lab settings (with ground-truth poses).

Related papers

• R3-Avatar: Record and Retrieve Temporal Codebook for Reconstructing Photorealistic Human Avatars [28.13595266126147]
  R3-Avatar overcomes the inability of human avatars to be both animatable and of high-fidelity rendering quality.<n>We adopt a "record-retrieve-reconstruct" strategy that ensures high-fidelity rendering from novel views while mitigating degradation in novel poses.
  arXiv  Detail & Related papers  (2025-03-17T02:38:13Z)
• Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior [31.780579293685797]
  We present Vid2Avatar-Pro, a method to create photorealistic and animatable 3D human avatars from monocular in-the-wild videos.
  arXiv  Detail & Related papers  (2025-03-03T14:45:35Z)
• WonderHuman: Hallucinating Unseen Parts in Dynamic 3D Human Reconstruction [63.666166249633385]
  We present WonderHuman to reconstruct dynamic human avatars from a monocular video for high-fidelity novel view synthesis.<n>Our method achieves SOTA performance in producing photorealistic renderings from the given monocular video.
  arXiv  Detail & Related papers  (2025-02-03T04:43:41Z)
• IDOL: Instant Photorealistic 3D Human Creation from a Single Image [47.51400420928373]
  This work rethinks the task from the perspectives of dataset, model, and representation.<n>We introduce a large-scale HUman-centric GEnerated dataset, HuGe100K, consisting of 100K diverse, photorealistic sets of human images.<n>We develop a scalable feed-forward transformer model to predict a 3D human Gaussian representation in a uniform space from a given human image.
  arXiv  Detail & Related papers  (2024-12-19T15:43:05Z)
• AvatarPose: Avatar-guided 3D Pose Estimation of Close Human Interaction from Sparse Multi-view Videos [31.904839609743448]
  Existing multi-view methods often face challenges in estimating the 3D pose and shape of multiple closely interacting people. We propose a novel method leveraging the personalized implicit neural avatar of each individual as a prior. Our experimental results demonstrate state-of-the-art performance on several public datasets.
  arXiv  Detail & Related papers  (2024-08-04T18:41:35Z)
• WildAvatar: Learning In-the-wild 3D Avatars from the Web [55.85887047136534]
  We propose an annotating pipeline with filtering protocols to curate humans from the web.<n>We then curate WildAvatar, a web-scale in-the-wild human avatar creation dataset extracted from YouTube.<n>WildAvatar is at least $10times$ richer than previous datasets for 3D human avatar creation and closer to the real world.
  arXiv  Detail & Related papers  (2024-07-02T11:17:48Z)
• PuzzleAvatar: Assembling 3D Avatars from Personal Albums [54.831084076478874]
  We develop PuzzleAvatar, a novel model that generates a faithful 3D avatar from a personal OOTD album. We exploit the learned tokens as "puzzle pieces" from which we assemble a faithful, personalized 3D avatar.
  arXiv  Detail & Related papers  (2024-05-23T17:59:56Z)
• HAVE-FUN: Human Avatar Reconstruction from Few-Shot Unconstrained Images [33.298962236215964]
  We study the reconstruction of human avatars from a few-shot unconstrained photo album. For handling dynamic data, we integrate a skinning mechanism with deep marching tetrahedra. Our framework, called HaveFun, can undertake avatar reconstruction, rendering, and animation.
  arXiv  Detail & Related papers  (2023-11-27T10:01:31Z)
• Human from Blur: Human Pose Tracking from Blurry Images [89.65036443997103]
  We propose a method to estimate 3D human poses from substantially blurred images. Key idea is to tackle the inverse problem of image deblurring by modeling the forward problem with a 3D human model, a texture map, and a sequence of poses to describe human motion. Using a differentiable step, we can solve the inverse problem by backpropagating the pixel-wise reprojection error to recover the best human motion representation.
  arXiv  Detail & Related papers  (2023-03-30T08:05:59Z)
• MVP-Human Dataset for 3D Human Avatar Reconstruction from Unconstrained Frames [59.37430649840777]
  We present 3D Avatar Reconstruction in the wild (ARwild), which first reconstructs the implicit skinning fields in a multi-level manner. We contribute a large-scale dataset, MVP-Human, which contains 400 subjects, each of which has 15 scans in different poses. Overall, benefits from the specific network architecture and the diverse data, the trained model enables 3D avatar reconstruction from unconstrained frames.
  arXiv  Detail & Related papers  (2022-04-24T03:57:59Z)

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.