TRACE: High-Fidelity 3D Scene Editing via Tangible Reconstruction and Geometry-Aligned Contextual Video Masking
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908931658350592 |
|---|---|
| author | Hu, Jiyuan Zhang, Zechuan Yang, Zongxin Yang, Yi |
| author_facet | Hu, Jiyuan Zhang, Zechuan Yang, Zongxin Yang, Yi |
| contents | We present TRACE, a mesh-guided 3DGS editing framework that achieves automated, high-fidelity scene transformation. By anchoring video diffusion with explicit 3D geometry, TRACE uniquely enables fine-grained, part-level manipulatio--such as local pose shifting or component replacemen--while preserving the structural integrity of the central subject, a capability largely absent in existing editing methods. Our approach comprises three key stages: (1) Multi-view 3D-Anchor Synthesis, which leverages a sparse-view editor trained on our MV-TRACE datase--the first multi-view consistent dataset dedicated to scene-coherent object addition and modificatio--to generate spatially consistent 3D-anchors; (2) Tangible Geometry Anchoring (TGA), which ensures precise spatial synchronization between inserted meshes and the 3DGS scene via two-phase registration; and (3) Contextual Video Masking (CVM), which integrates 3D projections into an autoregressive video pipeline to achieve temporally stable, physically-grounded rendering. Extensive experiments demonstrate that TRACE consistently outperforms existing methods especially in editing versatility and structural integrity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_01207 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TRACE: High-Fidelity 3D Scene Editing via Tangible Reconstruction and Geometry-Aligned Contextual Video Masking Hu, Jiyuan Zhang, Zechuan Yang, Zongxin Yang, Yi Computer Vision and Pattern Recognition We present TRACE, a mesh-guided 3DGS editing framework that achieves automated, high-fidelity scene transformation. By anchoring video diffusion with explicit 3D geometry, TRACE uniquely enables fine-grained, part-level manipulatio--such as local pose shifting or component replacemen--while preserving the structural integrity of the central subject, a capability largely absent in existing editing methods. Our approach comprises three key stages: (1) Multi-view 3D-Anchor Synthesis, which leverages a sparse-view editor trained on our MV-TRACE datase--the first multi-view consistent dataset dedicated to scene-coherent object addition and modificatio--to generate spatially consistent 3D-anchors; (2) Tangible Geometry Anchoring (TGA), which ensures precise spatial synchronization between inserted meshes and the 3DGS scene via two-phase registration; and (3) Contextual Video Masking (CVM), which integrates 3D projections into an autoregressive video pipeline to achieve temporally stable, physically-grounded rendering. Extensive experiments demonstrate that TRACE consistently outperforms existing methods especially in editing versatility and structural integrity. |
| title | TRACE: High-Fidelity 3D Scene Editing via Tangible Reconstruction and Geometry-Aligned Contextual Video Masking |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.01207 |