Physically Controllable Relighting of Photographs

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Careaga, Chris, Aksoy, Yağız
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912526002814976
author Careaga, Chris
Aksoy, Yağız
author_facet Careaga, Chris
Aksoy, Yağız
contents We present a self-supervised approach to in-the-wild image relighting that enables fully controllable, physically based illumination editing. We achieve this by combining the physical accuracy of traditional rendering with the photorealistic appearance made possible by neural rendering. Our pipeline works by inferring a colored mesh representation of a given scene using monocular estimates of geometry and intrinsic components. This representation allows users to define their desired illumination configuration in 3D. The scene under the new lighting can then be rendered using a path-tracing engine. We send this approximate rendering of the scene through a feed-forward neural renderer to predict the final photorealistic relighting result. We develop a differentiable rendering process to reconstruct in-the-wild scene illumination, enabling self-supervised training of our neural renderer on raw image collections. Our method represents a significant step in bringing the explicit physical control over lights available in typical 3D computer graphics tools, such as Blender, to in-the-wild relighting.
format Preprint
id arxiv_https___arxiv_org_abs_2508_05626
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Physically Controllable Relighting of Photographs
Careaga, Chris
Aksoy, Yağız
Graphics
Computer Vision and Pattern Recognition
I.4
We present a self-supervised approach to in-the-wild image relighting that enables fully controllable, physically based illumination editing. We achieve this by combining the physical accuracy of traditional rendering with the photorealistic appearance made possible by neural rendering. Our pipeline works by inferring a colored mesh representation of a given scene using monocular estimates of geometry and intrinsic components. This representation allows users to define their desired illumination configuration in 3D. The scene under the new lighting can then be rendered using a path-tracing engine. We send this approximate rendering of the scene through a feed-forward neural renderer to predict the final photorealistic relighting result. We develop a differentiable rendering process to reconstruct in-the-wild scene illumination, enabling self-supervised training of our neural renderer on raw image collections. Our method represents a significant step in bringing the explicit physical control over lights available in typical 3D computer graphics tools, such as Blender, to in-the-wild relighting.
title Physically Controllable Relighting of Photographs
topic Graphics
Computer Vision and Pattern Recognition
I.4
url https://arxiv.org/abs/2508.05626