ScribbleLight: Single Image Indoor Relighting with Scribbles

TL;DR

ScribbleLight is a novel generative model that allows fine-grained, local control of indoor lighting effects from a single image using scribbles, enhancing virtual relighting with preserved textures and geometry.

Contribution

It introduces an Albedo-conditioned Stable Diffusion model combined with ControlNet architecture for detailed, geometry-preserving indoor relighting from minimal scribble annotations.

Findings

Supports diverse lighting effects like turning lights on/off and adding shadows.

Preserves original image textures and colors after relighting.

Enables local lighting control with sparse scribbles.

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.