Metraipolis › archive › dc_90da2d540adf
DecomVoxel: Harnessing 3D-Native Priors with Guided In-situ Denoising Optimization for Decompositional Scene Reconstruction — arXiv:2610.01914
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.01914
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T19:14:54.182Z
- SHA-256 of the archived text
b036fbd504edb1ad7002fe21b194e9472671f63e34315498727b1b3ef9842d55- Stable URL of this page
https://metraipolis.com/documento/dc_90da2d540adf
How to cite
DecomVoxel: Harnessing 3D-Native Priors with Guided In-situ Denoising Optimization for Decompositional Scene Reconstruction — arXiv:2610.01914 — arXiv (en), https://arxiv.org/abs/2610.01914 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_90da2d540adf (Metraipolis archive dc_90da2d540adf, sha256 b036fbd504edb1ad7002fe21b194e9472671f63e34315498727b1b3ef9842d55)
BibTeX
@misc{dc90da2d540adf,
title = {DecomVoxel: Harnessing 3D-Native Priors with Guided In-situ Denoising Optimization for Decompositional Scene Reconstruction — arXiv:2610.01914},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.01914},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_90da2d540adf; sha256 b036fbd504edb1ad7002fe21b194e9472671f63e34315498727b1b3ef9842d55},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01914. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Decompositional scene reconstruction aims to reconstruct high-quality objects and background, yet existing methods still struggle with the level of quality under heavy occlusions. While generative priors offer a potential solution, 2D image-based priors often suffer from multi-view inconsistency due to a lack of 3D awareness. Conversely, 3D-native priors provide stronger structural inductive biases but frequently lead to spatial drift and misalignment within complex scenes. To address these issues, we propose DecomVoxel, formulating object completion as a guided in-situ denoising optimization that bridges 3D-native priors with neural scene reconstruction. Our framework introduces a reformulated epsilon-based distillation loss to ensure stable latent refinement, alongside adaptive spatial guidance that utilizes occupied and vacant anchors with temporal annealing to suppress generative hallucinations and mitigate spatial drift. Experiments on Replica and ScanNet++ show that DecomVoxel significantly outperforms state-of-the-art methods while faithfully preserving the original spatial layout, structural fidelity, and style-consistent texture. Our method pushes the boundary of decompositional reconstruction by delivering high-quality textured meshes with clean topology, geometry, and appearance, providing a robust solution for the decompositional reconstruction of complex real-world scenes. Code is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.01914 — 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 2026-10-06T17:37:36.855Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).