TensorX
返回文献探索

Paper · arXiv 2505.09608

LightLab: Controlling Light Sources in Images with Diffusion Models

Nadav Magar, Amir Hertz, Eric Tabellion, Yael Pritch, Alex Rav-Acha, Ariel Shamir, Yedid Hoshen

38 upvotesMay 14, 2025arXiv 预印本
AI 摘要

A diffusion-based method fine-tuned on real and synthetic image pairs provides precise control over light sources and ambient illumination in images, offering more effective relighting than existing methods.

diffusion-based methodfine-tuningdiffusion modelrelightinginverse renderingphotorealistic priorlinearity of lightlight intensitylight colorlight editing

Abstract

We present a simple, yet effective diffusion-based method for fine-grained, parametric control over light sources in an image. Existing relighting methods either rely on multiple input views to perform inverse rendering at inference time, or fail to provide explicit control over light changes. Our method fine-tunes a diffusion model on a small set of real raw photograph pairs, supplemented by synthetically rendered images at scale, to elicit its photorealistic prior for relighting. We leverage the linearity of light to synthesize image pairs depicting controlled light changes of either a target light source or ambient illumination. Using this data and an appropriate fine-tuning scheme, we train a model for precise illumination changes with explicit control over light intensity and color. Lastly, we show how our method can achieve compelling light editing results, and outperforms existing methods based on user preference.

北京市昌平区探索星信息技术及软件开发工作室

京ICP备2026059466号
LightLab: Controlling Light Sources in Images with Diffusion Models | TensorX