Cora: Correspondence-aware image editing using few step diffusion
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915822423769088 |
|---|---|
| author | Alimohammadi, Amirhossein Mikaeili, Aryan Nag, Sauradip Hassanpour, Negar Tagliasacchi, Andrea Mahdavi-Amiri, Ali |
| author_facet | Alimohammadi, Amirhossein Mikaeili, Aryan Nag, Sauradip Hassanpour, Negar Tagliasacchi, Andrea Mahdavi-Amiri, Ali |
| contents | Image editing is an important task in computer graphics, vision, and VFX, with recent diffusion-based methods achieving fast and high-quality results. However, edits requiring significant structural changes, such as non-rigid deformations, object modifications, or content generation, remain challenging. Existing few step editing approaches produce artifacts such as irrelevant texture or struggle to preserve key attributes of the source image (e.g., pose). We introduce Cora, a novel editing framework that addresses these limitations by introducing correspondence-aware noise correction and interpolated attention maps. Our method aligns textures and structures between the source and target images through semantic correspondence, enabling accurate texture transfer while generating new content when necessary. Cora offers control over the balance between content generation and preservation. Extensive experiments demonstrate that, quantitatively and qualitatively, Cora excels in maintaining structure, textures, and identity across diverse edits, including pose changes, object addition, and texture refinements. User studies confirm that Cora delivers superior results, outperforming alternatives. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_23907 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Cora: Correspondence-aware image editing using few step diffusion Alimohammadi, Amirhossein Mikaeili, Aryan Nag, Sauradip Hassanpour, Negar Tagliasacchi, Andrea Mahdavi-Amiri, Ali Computer Vision and Pattern Recognition I.4.10; I.3.7; I.2.10 Image editing is an important task in computer graphics, vision, and VFX, with recent diffusion-based methods achieving fast and high-quality results. However, edits requiring significant structural changes, such as non-rigid deformations, object modifications, or content generation, remain challenging. Existing few step editing approaches produce artifacts such as irrelevant texture or struggle to preserve key attributes of the source image (e.g., pose). We introduce Cora, a novel editing framework that addresses these limitations by introducing correspondence-aware noise correction and interpolated attention maps. Our method aligns textures and structures between the source and target images through semantic correspondence, enabling accurate texture transfer while generating new content when necessary. Cora offers control over the balance between content generation and preservation. Extensive experiments demonstrate that, quantitatively and qualitatively, Cora excels in maintaining structure, textures, and identity across diverse edits, including pose changes, object addition, and texture refinements. User studies confirm that Cora delivers superior results, outperforming alternatives. |
| title | Cora: Correspondence-aware image editing using few step diffusion |
| topic | Computer Vision and Pattern Recognition I.4.10; I.3.7; I.2.10 |
| url | https://arxiv.org/abs/2505.23907 |