SpotLight: Shadow-Guided Object Relighting via Diffusion

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Fortier-Chouinard, Frédéric, Zhang, Zitian, Messier, Louis-Etienne, Garon, Mathieu, Bhattad, Anand, Lalonde, Jean-François
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911311786409984
author Fortier-Chouinard, Frédéric
Zhang, Zitian
Messier, Louis-Etienne
Garon, Mathieu
Bhattad, Anand
Lalonde, Jean-François
author_facet Fortier-Chouinard, Frédéric
Zhang, Zitian
Messier, Louis-Etienne
Garon, Mathieu
Bhattad, Anand
Lalonde, Jean-François
contents Recent work has shown that diffusion models can serve as powerful neural rendering engines that can be leveraged for inserting virtual objects into images. However, unlike typical physics-based renderers, these neural rendering engines are limited by the lack of manual control over the lighting, which is often essential for improving or personalizing the desired image outcome. In this paper, we show that precise and controllable lighting can be achieved without any additional training, simply by supplying a coarse shadow hint for the object. Indeed, we show that injecting only the desired shadow of the object into a pre-trained diffusion-based neural renderer enables it to accurately shade the object according to the desired light position, while properly harmonizing the object (and its shadow) within the target background image. Our method, SpotLight, is entirely training-free and leverages existing neural rendering approaches to achieve controllable relighting. We show that SpotLight achieves superior object compositing results, both quantitatively and perceptually, as confirmed by a user study, outperforming existing diffusion-based models specifically designed for relighting. We also demonstrate other applications, such as hand-scribbling shadows and full-image relighting, demonstrating its versatility.
format Preprint
id arxiv_https___arxiv_org_abs_2411_18665
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SpotLight: Shadow-Guided Object Relighting via Diffusion
Fortier-Chouinard, Frédéric
Zhang, Zitian
Messier, Louis-Etienne
Garon, Mathieu
Bhattad, Anand
Lalonde, Jean-François
Computer Vision and Pattern Recognition
Graphics
Recent work has shown that diffusion models can serve as powerful neural rendering engines that can be leveraged for inserting virtual objects into images. However, unlike typical physics-based renderers, these neural rendering engines are limited by the lack of manual control over the lighting, which is often essential for improving or personalizing the desired image outcome. In this paper, we show that precise and controllable lighting can be achieved without any additional training, simply by supplying a coarse shadow hint for the object. Indeed, we show that injecting only the desired shadow of the object into a pre-trained diffusion-based neural renderer enables it to accurately shade the object according to the desired light position, while properly harmonizing the object (and its shadow) within the target background image. Our method, SpotLight, is entirely training-free and leverages existing neural rendering approaches to achieve controllable relighting. We show that SpotLight achieves superior object compositing results, both quantitatively and perceptually, as confirmed by a user study, outperforming existing diffusion-based models specifically designed for relighting. We also demonstrate other applications, such as hand-scribbling shadows and full-image relighting, demonstrating its versatility.
title SpotLight: Shadow-Guided Object Relighting via Diffusion
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2411.18665