DisCo3D: Distilling Multi-View Consistency for 3D Scene Editing
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916878234943488 |
|---|---|
| author | Chi, Yufeng Ma, Huimin Wang, Kafeng Li, Jianmin |
| author_facet | Chi, Yufeng Ma, Huimin Wang, Kafeng Li, Jianmin |
| contents | While diffusion models have demonstrated remarkable progress in 2D image generation and editing, extending these capabilities to 3D editing remains challenging, particularly in maintaining multi-view consistency. Classical approaches typically update 3D representations through iterative refinement based on a single editing view. However, these methods often suffer from slow convergence and blurry artifacts caused by cross-view inconsistencies. Recent methods improve efficiency by propagating 2D editing attention features, yet still exhibit fine-grained inconsistencies and failure modes in complex scenes due to insufficient constraints. To address this, we propose \textbf{DisCo3D}, a novel framework that distills 3D consistency priors into a 2D editor. Our method first fine-tunes a 3D generator using multi-view inputs for scene adaptation, then trains a 2D editor through consistency distillation. The edited multi-view outputs are finally optimized into 3D representations via Gaussian Splatting. Experimental results show DisCo3D achieves stable multi-view consistency and outperforms state-of-the-art methods in editing quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_01684 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DisCo3D: Distilling Multi-View Consistency for 3D Scene Editing Chi, Yufeng Ma, Huimin Wang, Kafeng Li, Jianmin Computer Vision and Pattern Recognition While diffusion models have demonstrated remarkable progress in 2D image generation and editing, extending these capabilities to 3D editing remains challenging, particularly in maintaining multi-view consistency. Classical approaches typically update 3D representations through iterative refinement based on a single editing view. However, these methods often suffer from slow convergence and blurry artifacts caused by cross-view inconsistencies. Recent methods improve efficiency by propagating 2D editing attention features, yet still exhibit fine-grained inconsistencies and failure modes in complex scenes due to insufficient constraints. To address this, we propose \textbf{DisCo3D}, a novel framework that distills 3D consistency priors into a 2D editor. Our method first fine-tunes a 3D generator using multi-view inputs for scene adaptation, then trains a 2D editor through consistency distillation. The edited multi-view outputs are finally optimized into 3D representations via Gaussian Splatting. Experimental results show DisCo3D achieves stable multi-view consistency and outperforms state-of-the-art methods in editing quality. |
| title | DisCo3D: Distilling Multi-View Consistency for 3D Scene Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.01684 |