LightIt: Illumination Modeling and Control for Diffusion Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909149097361408 |
|---|---|
| author | Kocsis, Peter Philip, Julien Sunkavalli, Kalyan Nießner, Matthias Hold-Geoffroy, Yannick |
| author_facet | Kocsis, Peter Philip, Julien Sunkavalli, Kalyan Nießner, Matthias Hold-Geoffroy, Yannick |
| contents | We introduce LightIt, a method for explicit illumination control for image generation. Recent generative methods lack lighting control, which is crucial to numerous artistic aspects of image generation such as setting the overall mood or cinematic appearance. To overcome these limitations, we propose to condition the generation on shading and normal maps. We model the lighting with single bounce shading, which includes cast shadows. We first train a shading estimation module to generate a dataset of real-world images and shading pairs. Then, we train a control network using the estimated shading and normals as input. Our method demonstrates high-quality image generation and lighting control in numerous scenes. Additionally, we use our generated dataset to train an identity-preserving relighting model, conditioned on an image and a target shading. Our method is the first that enables the generation of images with controllable, consistent lighting and performs on par with specialized relighting state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_10615 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LightIt: Illumination Modeling and Control for Diffusion Models Kocsis, Peter Philip, Julien Sunkavalli, Kalyan Nießner, Matthias Hold-Geoffroy, Yannick Computer Vision and Pattern Recognition Graphics Machine Learning I.4.8; I.2.10 We introduce LightIt, a method for explicit illumination control for image generation. Recent generative methods lack lighting control, which is crucial to numerous artistic aspects of image generation such as setting the overall mood or cinematic appearance. To overcome these limitations, we propose to condition the generation on shading and normal maps. We model the lighting with single bounce shading, which includes cast shadows. We first train a shading estimation module to generate a dataset of real-world images and shading pairs. Then, we train a control network using the estimated shading and normals as input. Our method demonstrates high-quality image generation and lighting control in numerous scenes. Additionally, we use our generated dataset to train an identity-preserving relighting model, conditioned on an image and a target shading. Our method is the first that enables the generation of images with controllable, consistent lighting and performs on par with specialized relighting state-of-the-art methods. |
| title | LightIt: Illumination Modeling and Control for Diffusion Models |
| topic | Computer Vision and Pattern Recognition Graphics Machine Learning I.4.8; I.2.10 |
| url | https://arxiv.org/abs/2403.10615 |