UniLight: A Unified Representation for Lighting
By: Zitian Zhang , Iliyan Georgiev , Michael Fischer and more
Potential Business Impact:
Unifies different light descriptions for better image control.
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.
Similar Papers
UniModel: A Visual-Only Framework for Unified Multimodal Understanding and Generation
CV and Pattern Recognition
Makes computers see and create pictures from words.
UAVLight: A Benchmark for Illumination-Robust 3D Reconstruction in Unmanned Aerial Vehicle (UAV) Scenes
CV and Pattern Recognition
Fixes 3D pictures made from different lights.
UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback
CV and Pattern Recognition
Makes pictures and videos look real with new lighting.