View-Consistent 3D Scene Editing via Dual-Path Structural Correspondense and Semantic Continuity
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911621008326656 |
|---|---|
| author | Li, Pufan Du, Bi'an Zheng, Shenghe Yao, Junyi Hu, Wei |
| author_facet | Li, Pufan Du, Bi'an Zheng, Shenghe Yao, Junyi Hu, Wei |
| contents | Text-driven 3D scene editing has recently attracted increasing attention. Most existing methods follow a render-edit-optimize pipeline, where multi-view images are rendered from a 3D scene, edited with 2D image editors, and then used to optimize the underlying 3D representation. However, cross-view inconsistency remains a major bottleneck. Although recent methods introduce geometric cues, cross-view interactions, or video priors to mitigate this issue, they still largely rely on inference-time synchronization and thus remain limited in robustness and generalization.In this work, we recast multi-view consistent 3D editing from a distributional perspective: 3D scene editing essentially requires a joint distribution modeling across viewpoints.Based on this insight, we propose a view-consistent 3D editing framework that explicitly introduces cross-view dependencies into the editing process. Furthermore, motivated by the observation that structural correspondence and semantic continuity rely on different cross-view cues, we introduce a dual-path consistency mechanism consisting of projection-guided structural guidance and patch-level semantic propagation for effective cross-view editing. Further, we construct a paired multi-view editing dataset that provides reliable supervision for learning cross-view consistency in edited scenes. Extensive experiments demonstrate that our method achieves superior editing performance with precise and consistent views for complex scenes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_17801 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | View-Consistent 3D Scene Editing via Dual-Path Structural Correspondense and Semantic Continuity Li, Pufan Du, Bi'an Zheng, Shenghe Yao, Junyi Hu, Wei Computer Vision and Pattern Recognition I.4.0 Text-driven 3D scene editing has recently attracted increasing attention. Most existing methods follow a render-edit-optimize pipeline, where multi-view images are rendered from a 3D scene, edited with 2D image editors, and then used to optimize the underlying 3D representation. However, cross-view inconsistency remains a major bottleneck. Although recent methods introduce geometric cues, cross-view interactions, or video priors to mitigate this issue, they still largely rely on inference-time synchronization and thus remain limited in robustness and generalization.In this work, we recast multi-view consistent 3D editing from a distributional perspective: 3D scene editing essentially requires a joint distribution modeling across viewpoints.Based on this insight, we propose a view-consistent 3D editing framework that explicitly introduces cross-view dependencies into the editing process. Furthermore, motivated by the observation that structural correspondence and semantic continuity rely on different cross-view cues, we introduce a dual-path consistency mechanism consisting of projection-guided structural guidance and patch-level semantic propagation for effective cross-view editing. Further, we construct a paired multi-view editing dataset that provides reliable supervision for learning cross-view consistency in edited scenes. Extensive experiments demonstrate that our method achieves superior editing performance with precise and consistent views for complex scenes. |
| title | View-Consistent 3D Scene Editing via Dual-Path Structural Correspondense and Semantic Continuity |
| topic | Computer Vision and Pattern Recognition I.4.0 |
| url | https://arxiv.org/abs/2604.17801 |