Research map / Image generation / Image restoration
Scaling In-the-Wild Training for Diffusion-based Illumination Harmonization and Editing by Imposing Consistent Light Transport
Lvmin Zhang, Anyi Rao, Maneesh Agrawala
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Scales in-the-wild training of diffusion-based models for illumination harmonization and editing by imposing consistent light transport constraints to preserve image details and intrinsic properties like albedo.
Problem
Training diffusion-based illumination editing models at scale is hard because preserving underlying image details and intrinsic properties such as albedo is difficult without appropriate constraints.
Approach
Imposes consistent light transport constraints during training of large diffusion image models on in-the-wild data so that illumination is edited while intrinsic properties such as albedo remain unchanged.
Closest papers by meaning
- DiffusionLight: Light Probes for Free by Painting a Chrome Ball (CVPR 2024 · similarity 0.88)
- LightIt: Illumination Modeling and Control for Diffusion Models (CVPR 2024 · similarity 0.88)
- Neural LightRig: Unlocking Accurate Object Normal and Material Estimation with Multi-Light Diffusion (CVPR 2025 · similarity 0.88)
- Zero-Reference Low-Light Enhancement via Physical Quadruple Priors (CVPR 2024 · similarity 0.88)
- Diffusion Renderer: Neural Inverse and Forward Rendering with Video Diffusion Models (CVPR 2025 · similarity 0.88)
- SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic Faces (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
