Metraipolis › archive › dc_cf05c346d784

Gaussian Sculpting: End-to-End Controllable Surface Reconstruction via Field Optimization — arXiv:2608.10602

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.10602
License (as archived)
CC0-1.0
Archived
2026-10-19T06:30:22.024Z
SHA-256 of the archived text
94690aacca9ca3722270e992492a5d43b0ea40dc008b2bfeb9b608743c453a05
Stable URL of this page
https://metraipolis.com/documento/dc_cf05c346d784

How to cite

Gaussian Sculpting: End-to-End Controllable Surface Reconstruction via Field Optimization — arXiv:2608.10602 — arXiv (en), https://arxiv.org/abs/2608.10602 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cf05c346d784 (Metraipolis archive dc_cf05c346d784, sha256 94690aacca9ca3722270e992492a5d43b0ea40dc008b2bfeb9b608743c453a05)
BibTeX
@misc{dccf05c346d784,
  title = {Gaussian Sculpting: End-to-End Controllable Surface Reconstruction via Field Optimization — arXiv:2608.10602},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10602},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cf05c346d784; sha256 94690aacca9ca3722270e992492a5d43b0ea40dc008b2bfeb9b608743c453a05},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10602. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

3D Gaussian Splatting (3DGS) has recently enabled real-time novel view synthesis with impressive quality. However, it struggles to recover accurate surfaces under limited viewpoints and due to the inherent irregularity of Gaussian primitives. The resulting geometric errors are notoriously difficult to correct manually. To address these issues, we propose Gaussian Sculpting, a fully differentiable end-to-end framework for high-quality surface reconstruction. Our key insight is to anchor Gaussians onto an evolving differentiable surface, allowing them to guide signed distance field (SDF) optimization instead of extracting the surface only during post-processing. To enable stable gradient isolation during joint optimization, we design a bi-level training strategy in which the outer loop optimizes the geometry represented by the SDF, while the inner loop updates the Gaussians with the geometry fixed. We further impose constraints on Gaussian parameters to ensure consistency with the underlying surface, thereby improving both geometric and appearance fidelity during optimization. In addition, we introduce a multi-resolution subdivision scheme based on octree-like partitioning to preserve fine details while reducing memory consumption. Experiments on object-level scenes demonstrate that our method effectively removes redundant surfaces, recovers missing structures caused by limited viewpoints, and achieves strong reconstruction quality even at relatively low resolutions.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-12 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Graphics (cs.GR).
Pagina del lavoro: https://arxiv.org/abs/2608.10602 — 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 2026-10-19T06:25:27.264Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).