LightLab: Controlling Light Sources in Images with Diffusion 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_ | 1866912376231559168 |
|---|---|
| author | Magar, Nadav Hertz, Amir Tabellion, Eric Pritch, Yael Rav-Acha, Alex Shamir, Ariel Hoshen, Yedid |
| author_facet | Magar, Nadav Hertz, Amir Tabellion, Eric Pritch, Yael Rav-Acha, Alex Shamir, Ariel Hoshen, Yedid |
| contents | We present a simple, yet effective diffusion-based method for fine-grained, parametric control over light sources in an image. Existing relighting methods either rely on multiple input views to perform inverse rendering at inference time, or fail to provide explicit control over light changes. Our method fine-tunes a diffusion model on a small set of real raw photograph pairs, supplemented by synthetically rendered images at scale, to elicit its photorealistic prior for relighting. We leverage the linearity of light to synthesize image pairs depicting controlled light changes of either a target light source or ambient illumination. Using this data and an appropriate fine-tuning scheme, we train a model for precise illumination changes with explicit control over light intensity and color. Lastly, we show how our method can achieve compelling light editing results, and outperforms existing methods based on user preference. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_09608 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LightLab: Controlling Light Sources in Images with Diffusion Models Magar, Nadav Hertz, Amir Tabellion, Eric Pritch, Yael Rav-Acha, Alex Shamir, Ariel Hoshen, Yedid Computer Vision and Pattern Recognition Graphics We present a simple, yet effective diffusion-based method for fine-grained, parametric control over light sources in an image. Existing relighting methods either rely on multiple input views to perform inverse rendering at inference time, or fail to provide explicit control over light changes. Our method fine-tunes a diffusion model on a small set of real raw photograph pairs, supplemented by synthetically rendered images at scale, to elicit its photorealistic prior for relighting. We leverage the linearity of light to synthesize image pairs depicting controlled light changes of either a target light source or ambient illumination. Using this data and an appropriate fine-tuning scheme, we train a model for precise illumination changes with explicit control over light intensity and color. Lastly, we show how our method can achieve compelling light editing results, and outperforms existing methods based on user preference. |
| title | LightLab: Controlling Light Sources in Images with Diffusion Models |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2505.09608 |