ScribbleLight: Single Image Indoor Relighting with Scribbles

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Choi, Jun Myeong, Wang, Annie, Peers, Pieter, Bhattad, Anand, Sengupta, Roni
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910717085483008
author Choi, Jun Myeong
Wang, Annie
Peers, Pieter
Bhattad, Anand
Sengupta, Roni
author_facet Choi, Jun Myeong
Wang, Annie
Peers, Pieter
Bhattad, Anand
Sengupta, Roni
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_17696
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ScribbleLight: Single Image Indoor Relighting with Scribbles
Choi, Jun Myeong
Wang, Annie
Peers, Pieter
Bhattad, Anand
Sengupta, Roni
Computer Vision and Pattern Recognition
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.
title ScribbleLight: Single Image Indoor Relighting with Scribbles
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.17696