Metraipolis › archive › dc_5e765e57cd55

Coarse3D: Controllable and Faithful Sparse Structure Generation for Image-to-3D — arXiv:2610.41231

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41231
License (as archived)
CC0-1.0
Archived
2026-11-03T07:33:14.178Z
SHA-256 of the archived text
5973fb180d6009ecbf34d16f02e4160d4bcf0786ba5782a5c7609a42e0be7f7f
Stable URL of this page
https://metraipolis.com/documento/dc_5e765e57cd55

How to cite

Coarse3D: Controllable and Faithful Sparse Structure Generation for Image-to-3D — arXiv:2610.41231 — arXiv (en), https://arxiv.org/abs/2610.41231 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5e765e57cd55 (Metraipolis archive dc_5e765e57cd55, sha256 5973fb180d6009ecbf34d16f02e4160d4bcf0786ba5782a5c7609a42e0be7f7f)
BibTeX
@misc{dc5e765e57cd55,
  title = {Coarse3D: Controllable and Faithful Sparse Structure Generation for Image-to-3D — arXiv:2610.41231},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41231},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5e765e57cd55; sha256 5973fb180d6009ecbf34d16f02e4160d4bcf0786ba5782a5c7609a42e0be7f7f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41231. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Coarse-to-fine 3D-native generation relies heavily on the first-stage sparse structure, which determines the global orientation and overall geometry for subsequent refinement. However, existing coarse generators suffer from two key limitations: their orientation is difficult to control due to ambiguous semantic canonicalization, and their structures are often inconsistent with input images due to weak 2D-3D grounding. We propose Coarse3D, a sparse-structure generation model that produces orientation-controllable and structurally faithful voxel geometry from arbitrary unposed images. Coarse3D introduces three designs: a first-frame anchored canonical space that aligns generation with the first input view while preserving object-centric normalization; a dual-tower DiT that couples generation with auxiliary feed-forward reconstruction to learn spatially grounded features; and spatial-prior guided attention that regularizes cross-attention with pixel-to-voxel correspondence. Coarse3D can directly replace the coarse stage of existing pipelines. Experiments show that it substantially improves sparse structure quality and consistently enhances final 3D generation, achieving state-of-the-art performance.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.41231 — 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 2026-11-03T07:29:33.715Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).