EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DecomVoxel: Harnessing 3D-Native Priors with Guided In-situ Denoising Optimization for Decompositional Scene Reconstruction

Junfeng Ni, Zirui Zhou, Yixin Chen, Yu Liu, Nan Jiang, Zhifei Yang, Song-Chun Zhu, Siyuan Huang

ACM Transactions on Graphics · 09.11.2026 · 45 (6) · 1-12

DOI: 10.1145/3842522 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 09.11.2026. Verfasst von Junfeng Ni und 7 weiteren Autor:innen. Die Arbeit nennt 87 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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 https://github.com/DecomVoxel/DecomVoxel.

Zitieren

APA

Ni, J., Zhou, Z., Chen, Y., Liu, Y., Jiang, N., Yang, Z., Zhu, S., & Huang, S. (2026). DecomVoxel: Harnessing 3D-Native Priors with Guided In-situ Denoising Optimization for Decompositional Scene Reconstruction. ACM Transactions on Graphics, 45(6), 1-12. https://doi.org/10.1145/3842522

Vancouver

Ni J, Zhou Z, Chen Y, Liu Y, Jiang N, Yang Z, et al. DecomVoxel: Harnessing 3D-Native Priors with Guided In-situ Denoising Optimization for Decompositional Scene Reconstruction. ACM Transactions on Graphics. 2026;45(6):1-12. doi:10.1145/3842522

BibTeX
@article{Ni2026,
  author = {Ni, Junfeng and Zhou, Zirui and Chen, Yixin and Liu, Yu and Jiang, Nan and Yang, Zhifei and Zhu, Song-Chun and Huang, Siyuan},
  title = {DecomVoxel: Harnessing 3D-Native Priors with Guided In-situ Denoising Optimization for Decompositional Scene Reconstruction},
  journal = {ACM Transactions on Graphics},
  year = {2026},
  volume = {45},
  number = {6},
  pages = {1--12},
  doi = {10.1145/3842522}
}
Kostenlos starten →