UniLight: A Unified Representation for Lighting

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Zitian, Georgiev, Iliyan, Fischer, Michael, Hold-Geoffroy, Yannick, Lalonde, Jean-François, Deschaintre, Valentin
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908864394297344
author Zhang, Zitian
Georgiev, Iliyan
Fischer, Michael
Hold-Geoffroy, Yannick
Lalonde, Jean-François
Deschaintre, Valentin
author_facet Zhang, Zitian
Georgiev, Iliyan
Fischer, Michael
Hold-Geoffroy, Yannick
Lalonde, Jean-François
Deschaintre, Valentin
contents Lighting has a strong influence on visual appearance, yet understanding and representing lighting in images remains notoriously difficult. Various lighting representations exist, such as environment maps, irradiance, spherical harmonics, or text, but they are incompatible, which limits cross-modal transfer. We thus propose UniLight, a joint latent space as lighting representation, that unifies multiple modalities within a shared embedding. Modality-specific encoders for text, images, irradiance, and environment maps are trained contrastively to align their representations, with an auxiliary spherical-harmonics prediction task reinforcing directional understanding. Our multi-modal data pipeline enables large-scale training and evaluation across three tasks: lighting-based retrieval, environment-map generation, and lighting control in diffusion-based image synthesis. Experiments show that our representation captures consistent and transferable lighting features, enabling flexible manipulation across modalities.
format Preprint
id arxiv_https___arxiv_org_abs_2512_04267
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UniLight: A Unified Representation for Lighting
Zhang, Zitian
Georgiev, Iliyan
Fischer, Michael
Hold-Geoffroy, Yannick
Lalonde, Jean-François
Deschaintre, Valentin
Computer Vision and Pattern Recognition
Lighting has a strong influence on visual appearance, yet understanding and representing lighting in images remains notoriously difficult. Various lighting representations exist, such as environment maps, irradiance, spherical harmonics, or text, but they are incompatible, which limits cross-modal transfer. We thus propose UniLight, a joint latent space as lighting representation, that unifies multiple modalities within a shared embedding. Modality-specific encoders for text, images, irradiance, and environment maps are trained contrastively to align their representations, with an auxiliary spherical-harmonics prediction task reinforcing directional understanding. Our multi-modal data pipeline enables large-scale training and evaluation across three tasks: lighting-based retrieval, environment-map generation, and lighting control in diffusion-based image synthesis. Experiments show that our representation captures consistent and transferable lighting features, enabling flexible manipulation across modalities.
title UniLight: A Unified Representation for Lighting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.04267