"ScribbleLight: Single Image Indoor Relighting with Scribbles"
IEEE International Conference on Computer Vision and Pattern Recognition, June 2025
Abstract
Image-based relighting of indoor rooms creates an immersive virtual understanding of the space, which is useful for interior design, virtual staging, and real estate. Relighting indoor rooms from a single image is especially challenging due to complex illumination interactions between multiple lights and cluttered objects featuring a large variety in geometrical and material complexity. Recently, generative models have been successfully applied to image-based relighting conditioned on a target image or a latent code, albeit without detailed local lighting control. In this paper, we introduce ScribbleLight, a generative model that supports local fine-grained control of lighting effects through scribbles that describe changes in lighting. Our key technical novelty is an Albedo-conditioned Stable Image Diffusion model that preserves the intrinsic color and texture of the original image after relighting and an encoder-decoder-based ControlNet architecture that enables geometry-preserving lighting effects with normal map and scribble annotations. We demonstrate ScribbleLight's ability to create different lighting effects (e.g., turning lights on/off, adding highlights, cast shadows, or indirect lighting from unseen lights) from sparse scribble annotations.
Download
Supplementary Material
Code
Related Publications
Bibtex
IEEE International Conference on Computer Vision and Pattern Recognition, June 2025
AbstractImage-based relighting of indoor rooms creates an immersive virtual understanding of the space, which is useful for interior design, virtual staging, and real estate. Relighting indoor rooms from a single image is especially challenging due to complex illumination interactions between multiple lights and cluttered objects featuring a large variety in geometrical and material complexity. Recently, generative models have been successfully applied to image-based relighting conditioned on a target image or a latent code, albeit without detailed local lighting control. In this paper, we introduce ScribbleLight, a generative model that supports local fine-grained control of lighting effects through scribbles that describe changes in lighting. Our key technical novelty is an Albedo-conditioned Stable Image Diffusion model that preserves the intrinsic color and texture of the original image after relighting and an encoder-decoder-based ControlNet architecture that enables geometry-preserving lighting effects with normal map and scribble annotations. We demonstrate ScribbleLight's ability to create different lighting effects (e.g., turning lights on/off, adding highlights, cast shadows, or indirect lighting from unseen lights) from sparse scribble annotations.
Download
- Choi_CVPR2025.pdf (44.98Mb)
Supplementary Material
- External Supplemental Material (link)
Code
- Code Repository (github)
Related Publications
-
"ScribbleLight: Single Image Indoor Relighting with Scribbles",
CoRR, abs/2411.17696,
November 2024,
@conference{Choi:2025:SSI,
author = {Choi, Jun Myeong and Wang, Annie and Peers, Pieter and Bhattad, Anand and Sengupta, Roni},
title = {ScribbleLight: Single Image Indoor Relighting with Scribbles},
month = {June},
year = {2025},
booktitle = {IEEE International Conference on Computer Vision and Pattern Recognition},
}
author = {Choi, Jun Myeong and Wang, Annie and Peers, Pieter and Bhattad, Anand and Sengupta, Roni},
title = {ScribbleLight: Single Image Indoor Relighting with Scribbles},
month = {June},
year = {2025},
booktitle = {IEEE International Conference on Computer Vision and Pattern Recognition},
}