Diffusion-Based Attention Warping for Consistent 3D Scene Editing
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909424453419008 |
|---|---|
| author | Gomel, Eyal Wolf, Lior |
| author_facet | Gomel, Eyal Wolf, Lior |
| contents | We present a novel method for 3D scene editing using diffusion models, designed to ensure view consistency and realism across perspectives. Our approach leverages attention features extracted from a single reference image to define the intended edits. These features are warped across multiple views by aligning them with scene geometry derived from Gaussian splatting depth estimates. Injecting these warped features into other viewpoints enables coherent propagation of edits, achieving high fidelity and spatial alignment in 3D space. Extensive evaluations demonstrate the effectiveness of our method in generating versatile edits of 3D scenes, significantly advancing the capabilities of scene manipulation compared to the existing methods. Project page: \url{https://attention-warp.github.io} |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_07984 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Diffusion-Based Attention Warping for Consistent 3D Scene Editing Gomel, Eyal Wolf, Lior Computer Vision and Pattern Recognition We present a novel method for 3D scene editing using diffusion models, designed to ensure view consistency and realism across perspectives. Our approach leverages attention features extracted from a single reference image to define the intended edits. These features are warped across multiple views by aligning them with scene geometry derived from Gaussian splatting depth estimates. Injecting these warped features into other viewpoints enables coherent propagation of edits, achieving high fidelity and spatial alignment in 3D space. Extensive evaluations demonstrate the effectiveness of our method in generating versatile edits of 3D scenes, significantly advancing the capabilities of scene manipulation compared to the existing methods. Project page: \url{https://attention-warp.github.io} |
| title | Diffusion-Based Attention Warping for Consistent 3D Scene Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.07984 |