ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation
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_ | 1866912653479247872 |
|---|---|
| author | Wu, Jay Zhangjie Ren, Xuanchi Shen, Tianchang Cao, Tianshi He, Kai Lu, Yifan Gao, Ruiyuan Xie, Enze Lan, Shiyi Alvarez, Jose M. Gao, Jun Fidler, Sanja Wang, Zian Ling, Huan |
| author_facet | Wu, Jay Zhangjie Ren, Xuanchi Shen, Tianchang Cao, Tianshi He, Kai Lu, Yifan Gao, Ruiyuan Xie, Enze Lan, Shiyi Alvarez, Jose M. Gao, Jun Fidler, Sanja Wang, Zian Ling, Huan |
| contents | Recent advances in large generative models have greatly enhanced both image editing and in-context image generation, yet a critical gap remains in ensuring physical consistency, where edited objects must remain coherent. This capability is especially vital for world simulation related tasks. In this paper, we present ChronoEdit, a framework that reframes image editing as a video generation problem. First, ChronoEdit treats the input and edited images as the first and last frames of a video, allowing it to leverage large pretrained video generative models that capture not only object appearance but also the implicit physics of motion and interaction through learned temporal consistency. Second, ChronoEdit introduces a temporal reasoning stage that explicitly performs editing at inference time. Under this setting, target frame is jointly denoised with reasoning tokens to imagine a plausible editing trajectory that constrains the solution space to physically viable transformations. The reasoning tokens are then dropped after a few steps to avoid the high computational cost of rendering a full video. To validate ChronoEdit, we introduce PBench-Edit, a new benchmark of image-prompt pairs for contexts that require physical consistency, and demonstrate that ChronoEdit surpasses state-of-the-art baselines in both visual fidelity and physical plausibility. Project page for code and models: https://research.nvidia.com/labs/toronto-ai/chronoedit |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_04290 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation Wu, Jay Zhangjie Ren, Xuanchi Shen, Tianchang Cao, Tianshi He, Kai Lu, Yifan Gao, Ruiyuan Xie, Enze Lan, Shiyi Alvarez, Jose M. Gao, Jun Fidler, Sanja Wang, Zian Ling, Huan Computer Vision and Pattern Recognition Recent advances in large generative models have greatly enhanced both image editing and in-context image generation, yet a critical gap remains in ensuring physical consistency, where edited objects must remain coherent. This capability is especially vital for world simulation related tasks. In this paper, we present ChronoEdit, a framework that reframes image editing as a video generation problem. First, ChronoEdit treats the input and edited images as the first and last frames of a video, allowing it to leverage large pretrained video generative models that capture not only object appearance but also the implicit physics of motion and interaction through learned temporal consistency. Second, ChronoEdit introduces a temporal reasoning stage that explicitly performs editing at inference time. Under this setting, target frame is jointly denoised with reasoning tokens to imagine a plausible editing trajectory that constrains the solution space to physically viable transformations. The reasoning tokens are then dropped after a few steps to avoid the high computational cost of rendering a full video. To validate ChronoEdit, we introduce PBench-Edit, a new benchmark of image-prompt pairs for contexts that require physical consistency, and demonstrate that ChronoEdit surpasses state-of-the-art baselines in both visual fidelity and physical plausibility. Project page for code and models: https://research.nvidia.com/labs/toronto-ai/chronoedit |
| title | ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.04290 |