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.
We qualitatively compare the relighting quality of LightIt* [31], RGB↔X [73], and ScribbleLight (Ours) using user-provided hand-drawn scribbles.
Qualitative comparison of relighting quality between LightIt* [31], IIDiffusion [32], RGB↔X [73] and ScribbleLight (Ours) with monochromatic shading map given a target (GT) image
We illustrate ScribbleLight's ability to create various plausible relit images by switching different lights on and off while preserving the intrinsic properties of the input photograph.
@misc{choi2024scribblelightsingleimageindoor,
title={ScribbleLight: Single Image Indoor Relighting with Scribbles},
author={Jun Myeong Choi and Annie Wang and Pieter Peers and Anand Bhattad and Roni Sengupta},
year={2024},
eprint={2411.17696},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2411.17696},
}