Metraipolis › archive › dc_a242b2fe201b

DiGS-Avatar: Single-Image Animatable 3D Human Reconstruction via UV-Space Diffusion — arXiv:2608.20759

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.20759
License (as archived)
CC0-1.0
Archived
2026-10-18T10:52:55.341Z
SHA-256 of the archived text
23d39d2f33b278b69a7e63c45cb0ecc72de3d7436f6f865c35d5590aaa421b20
Stable URL of this page
https://metraipolis.com/documento/dc_a242b2fe201b

How to cite

DiGS-Avatar: Single-Image Animatable 3D Human Reconstruction via UV-Space Diffusion — arXiv:2608.20759 — arXiv (en), https://arxiv.org/abs/2608.20759 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a242b2fe201b (Metraipolis archive dc_a242b2fe201b, sha256 23d39d2f33b278b69a7e63c45cb0ecc72de3d7436f6f865c35d5590aaa421b20)
BibTeX
@misc{dca242b2fe201b,
  title = {DiGS-Avatar: Single-Image Animatable 3D Human Reconstruction via UV-Space Diffusion — arXiv:2608.20759},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.20759},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a242b2fe201b; sha256 23d39d2f33b278b69a7e63c45cb0ecc72de3d7436f6f865c35d5590aaa421b20},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20759. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Single-image 3D human reconstruction often suffers from over-smoothed textures and geometric inconsistencies. While diffusion models improve generative quality, their reliance on multi-view synthesis prior to 3D reconstruction is computationally expensive and prone to view inconsistency. We propose DiGS-Avatar, which reformulates this task as an efficient, diffusion-based UV-latent completion task, ensuring 3D consistency by design. To capture accurate spatial structure, we introduce a teacher-student framework where a multi-view teacher provides geometrically aligned pseudo-ground-truth latents to supervise a single-view diffusion student. Treating this inferred latent as a robust structural skeleton, our method injects high-level semantic features to accurately recover fine textural details without disrupting spatial integrity. The refined representation is then decoded into 3D Gaussian primitives. Extensive experiments demonstrate that DiGS-Avatar achieves state-of-the-art or highly competitive visual fidelity and zero-shot generalization, while reconstructing a fully animatable 3D avatar in just 0.71 seconds. Code is available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-24 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.20759 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T10:48:13.563Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).