When Test-Time Guidance Is Enough: Fast Image and Video Editing with Diffusion Guidance
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_ | 1866917371046789120 |
|---|---|
| author | Ghorbel, Ahmed Moufad, Badr Shouraki, Navid Bagheri Durmus, Alain Oliviero Hirtz, Thomas Moulines, Eric Olsson, Jimmy Janati, Yazid |
| author_facet | Ghorbel, Ahmed Moufad, Badr Shouraki, Navid Bagheri Durmus, Alain Oliviero Hirtz, Thomas Moulines, Eric Olsson, Jimmy Janati, Yazid |
| contents | Text-driven image and video editing can be naturally cast as inpainting problems, where masked regions are reconstructed to remain consistent with both the observed content and the editing prompt. Recent advances in test-time guidance for diffusion and flow models provide a principled framework for this task; however, existing methods rely on costly vector--Jacobian product (VJP) computations to approximate the intractable guidance term, limiting their practical applicability. Building upon the recent work of Moufad et al. (2025), we provide theoretical insights into their VJP-free approximation and substantially extend their empirical evaluation to large-scale image and video editing benchmarks. Our results demonstrate that test-time guidance alone can achieve performance comparable to, and in some cases surpass, training-based methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_14157 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | When Test-Time Guidance Is Enough: Fast Image and Video Editing with Diffusion Guidance Ghorbel, Ahmed Moufad, Badr Shouraki, Navid Bagheri Durmus, Alain Oliviero Hirtz, Thomas Moulines, Eric Olsson, Jimmy Janati, Yazid Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Text-driven image and video editing can be naturally cast as inpainting problems, where masked regions are reconstructed to remain consistent with both the observed content and the editing prompt. Recent advances in test-time guidance for diffusion and flow models provide a principled framework for this task; however, existing methods rely on costly vector--Jacobian product (VJP) computations to approximate the intractable guidance term, limiting their practical applicability. Building upon the recent work of Moufad et al. (2025), we provide theoretical insights into their VJP-free approximation and substantially extend their empirical evaluation to large-scale image and video editing benchmarks. Our results demonstrate that test-time guidance alone can achieve performance comparable to, and in some cases surpass, training-based methods. |
| title | When Test-Time Guidance Is Enough: Fast Image and Video Editing with Diffusion Guidance |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2602.14157 |