DiffusionLight: Light Probes for Free by Painting a Chrome Ball

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Phongthawee, Pakkapon, Chinchuthakun, Worameth, Sinsunthithet, Nontaphat, Raj, Amit, Jampani, Varun, Khungurn, Pramook, Suwajanakorn, Supasorn
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916198165250048
author Phongthawee, Pakkapon
Chinchuthakun, Worameth
Sinsunthithet, Nontaphat
Raj, Amit
Jampani, Varun
Khungurn, Pramook
Suwajanakorn, Supasorn
author_facet Phongthawee, Pakkapon
Chinchuthakun, Worameth
Sinsunthithet, Nontaphat
Raj, Amit
Jampani, Varun
Khungurn, Pramook
Suwajanakorn, Supasorn
contents We present a simple yet effective technique to estimate lighting in a single input image. Current techniques rely heavily on HDR panorama datasets to train neural networks to regress an input with limited field-of-view to a full environment map. However, these approaches often struggle with real-world, uncontrolled settings due to the limited diversity and size of their datasets. To address this problem, we leverage diffusion models trained on billions of standard images to render a chrome ball into the input image. Despite its simplicity, this task remains challenging: the diffusion models often insert incorrect or inconsistent objects and cannot readily generate images in HDR format. Our research uncovers a surprising relationship between the appearance of chrome balls and the initial diffusion noise map, which we utilize to consistently generate high-quality chrome balls. We further fine-tune an LDR diffusion model (Stable Diffusion XL) with LoRA, enabling it to perform exposure bracketing for HDR light estimation. Our method produces convincing light estimates across diverse settings and demonstrates superior generalization to in-the-wild scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2312_09168
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle DiffusionLight: Light Probes for Free by Painting a Chrome Ball
Phongthawee, Pakkapon
Chinchuthakun, Worameth
Sinsunthithet, Nontaphat
Raj, Amit
Jampani, Varun
Khungurn, Pramook
Suwajanakorn, Supasorn
Computer Vision and Pattern Recognition
Graphics
Machine Learning
I.3.3; I.4.8
We present a simple yet effective technique to estimate lighting in a single input image. Current techniques rely heavily on HDR panorama datasets to train neural networks to regress an input with limited field-of-view to a full environment map. However, these approaches often struggle with real-world, uncontrolled settings due to the limited diversity and size of their datasets. To address this problem, we leverage diffusion models trained on billions of standard images to render a chrome ball into the input image. Despite its simplicity, this task remains challenging: the diffusion models often insert incorrect or inconsistent objects and cannot readily generate images in HDR format. Our research uncovers a surprising relationship between the appearance of chrome balls and the initial diffusion noise map, which we utilize to consistently generate high-quality chrome balls. We further fine-tune an LDR diffusion model (Stable Diffusion XL) with LoRA, enabling it to perform exposure bracketing for HDR light estimation. Our method produces convincing light estimates across diverse settings and demonstrates superior generalization to in-the-wild scenarios.
title DiffusionLight: Light Probes for Free by Painting a Chrome Ball
topic Computer Vision and Pattern Recognition
Graphics
Machine Learning
I.3.3; I.4.8
url https://arxiv.org/abs/2312.09168