NeuSEditor: From Multi-View Images to Text-Guided Neural Surface Edits
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908366972911616 |
|---|---|
| author | Ibrahimli, Nail Kooij, Julian F. P. Nan, Liangliang |
| author_facet | Ibrahimli, Nail Kooij, Julian F. P. Nan, Liangliang |
| contents | Implicit surface representations are valued for their compactness and continuity, but they pose significant challenges for editing. Despite recent advancements, existing methods often fail to preserve identity and maintain geometric consistency during editing. To address these challenges, we present NeuSEditor, a novel method for text-guided editing of neural implicit surfaces derived from multi-view images. NeuSEditor introduces an identity-preserving architecture that efficiently separates scenes into foreground and background, enabling precise modifications without altering the scene-specific elements. Our geometry-aware distillation loss significantly enhances rendering and geometric quality. Our method simplifies the editing workflow by eliminating the need for continuous dataset updates and source prompting. NeuSEditor outperforms recent state-of-the-art methods like PDS and InstructNeRF2NeRF, delivering superior quantitative and qualitative results. For more visual results, visit: neuseditor.github.io. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_10827 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | NeuSEditor: From Multi-View Images to Text-Guided Neural Surface Edits Ibrahimli, Nail Kooij, Julian F. P. Nan, Liangliang Computer Vision and Pattern Recognition Implicit surface representations are valued for their compactness and continuity, but they pose significant challenges for editing. Despite recent advancements, existing methods often fail to preserve identity and maintain geometric consistency during editing. To address these challenges, we present NeuSEditor, a novel method for text-guided editing of neural implicit surfaces derived from multi-view images. NeuSEditor introduces an identity-preserving architecture that efficiently separates scenes into foreground and background, enabling precise modifications without altering the scene-specific elements. Our geometry-aware distillation loss significantly enhances rendering and geometric quality. Our method simplifies the editing workflow by eliminating the need for continuous dataset updates and source prompting. NeuSEditor outperforms recent state-of-the-art methods like PDS and InstructNeRF2NeRF, delivering superior quantitative and qualitative results. For more visual results, visit: neuseditor.github.io. |
| title | NeuSEditor: From Multi-View Images to Text-Guided Neural Surface Edits |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.10827 |