Fine-grained Defocus Blur Control for Generative Image Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908706873016320 |
|---|---|
| author | Shrivastava, Ayush Barnes, Connelly Zhang, Xuaner Zhang, Lingzhi Owens, Andrew Amirghodsi, Sohrab Shechtman, Eli |
| author_facet | Shrivastava, Ayush Barnes, Connelly Zhang, Xuaner Zhang, Lingzhi Owens, Andrew Amirghodsi, Sohrab Shechtman, Eli |
| contents | Current text-to-image diffusion models excel at generating diverse, high-quality images, yet they struggle to incorporate fine-grained camera metadata such as precise aperture settings. In this work, we introduce a novel text-to-image diffusion framework that leverages camera metadata, or EXIF data, which is often embedded in image files, with an emphasis on generating controllable lens blur. Our method mimics the physical image formation process by first generating an all-in-focus image, estimating its monocular depth, predicting a plausible focus distance with a novel focus distance transformer, and then forming a defocused image with an existing differentiable lens blur model. Gradients flow backwards through this whole process, allowing us to learn without explicit supervision to generate defocus effects based on content elements and the provided EXIF data. At inference time, this enables precise interactive user control over defocus effects while preserving scene contents, which is not achievable with existing diffusion models. Experimental results demonstrate that our model enables superior fine-grained control without altering the depicted scene. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_06215 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fine-grained Defocus Blur Control for Generative Image Models Shrivastava, Ayush Barnes, Connelly Zhang, Xuaner Zhang, Lingzhi Owens, Andrew Amirghodsi, Sohrab Shechtman, Eli Computer Vision and Pattern Recognition Current text-to-image diffusion models excel at generating diverse, high-quality images, yet they struggle to incorporate fine-grained camera metadata such as precise aperture settings. In this work, we introduce a novel text-to-image diffusion framework that leverages camera metadata, or EXIF data, which is often embedded in image files, with an emphasis on generating controllable lens blur. Our method mimics the physical image formation process by first generating an all-in-focus image, estimating its monocular depth, predicting a plausible focus distance with a novel focus distance transformer, and then forming a defocused image with an existing differentiable lens blur model. Gradients flow backwards through this whole process, allowing us to learn without explicit supervision to generate defocus effects based on content elements and the provided EXIF data. At inference time, this enables precise interactive user control over defocus effects while preserving scene contents, which is not achievable with existing diffusion models. Experimental results demonstrate that our model enables superior fine-grained control without altering the depicted scene. |
| title | Fine-grained Defocus Blur Control for Generative Image Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.06215 |