Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.21499 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917356115066880 |
|---|---|
| author | Hu, Shimin Wei, Yuanyi Zha, Fei Guo, Yudong Zhang, Juyong |
| author_facet | Hu, Shimin Wei, Yuanyi Zha, Fei Guo, Yudong Zhang, Juyong |
| contents | Existing 3D editing methods rely on computationally intensive scene-by-scene iterative optimization and suffer from multi-view inconsistency. We propose an effective and feed-forward 3D editing framework based on the TRELLIS generative backbone, capable of modifying 3D models from a single editing view. Our framework addresses two key issues: adapting training-free 2D editing to structured 3D representations, and overcoming the bottleneck of appearance fidelity in compressed 3D features. To ensure geometric consistency, we introduce Voxel FlowEdit, an edit-driven flow in the sparse voxel latent space that achieves globally consistent 3D deformation in a single pass. To restore high-fidelity details, we develop a normal-guided single to multi-view generation module as an external appearance prior, successfully recovering high-frequency textures. Experiments demonstrate that our method enables fast, globally consistent, and high-fidelity 3D model editing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_21499 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Easy3E: Feed-Forward 3D Asset Editing via Rectified Voxel Flow Hu, Shimin Wei, Yuanyi Zha, Fei Guo, Yudong Zhang, Juyong Computer Vision and Pattern Recognition Existing 3D editing methods rely on computationally intensive scene-by-scene iterative optimization and suffer from multi-view inconsistency. We propose an effective and feed-forward 3D editing framework based on the TRELLIS generative backbone, capable of modifying 3D models from a single editing view. Our framework addresses two key issues: adapting training-free 2D editing to structured 3D representations, and overcoming the bottleneck of appearance fidelity in compressed 3D features. To ensure geometric consistency, we introduce Voxel FlowEdit, an edit-driven flow in the sparse voxel latent space that achieves globally consistent 3D deformation in a single pass. To restore high-fidelity details, we develop a normal-guided single to multi-view generation module as an external appearance prior, successfully recovering high-frequency textures. Experiments demonstrate that our method enables fast, globally consistent, and high-fidelity 3D model editing. |
| title | Easy3E: Feed-Forward 3D Asset Editing via Rectified Voxel Flow |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.21499 |