PI-Light: Physics-Inspired Diffusion for Full-Image Relighting

TL;DR

PI-Light introduces a physics-inspired diffusion framework for full-image relighting that enhances physical plausibility and generalization to real-world scenes through novel modules and a curated dataset.

Contribution

The paper presents a two-stage diffusion-based relighting method incorporating physics-guided modules and a new dataset, improving realism and generalization in image relighting.

Findings

Achieves superior relighting quality with specular highlights and diffuse reflections.

Demonstrates better generalization to real-world scenes than previous methods.

Enables efficient fine-tuning of pretrained diffusion models.

Abstract

Full-image relighting remains a challenging problem due to the difficulty of collecting large-scale structured paired data, the difficulty of maintaining physical plausibility, and the limited generalizability imposed by data-driven priors. Existing attempts to bridge the synthetic-to-real gap for full-scene relighting remain suboptimal. To tackle these challenges, we introduce Physics-Inspired diffusion for full-image reLight ($\pi$-Light, or PI-Light), a two-stage framework that leverages physics-inspired diffusion models. Our design incorporates (i) batch-aware attention, which improves the consistency of intrinsic predictions across a collection of images, (ii) a physics-guided neural rendering module that enforces physically plausible light transport, (iii) physics-inspired losses that regularize training dynamics toward a physically meaningful landscape, thereby enhancing generalizability to real-world image editing, and (iv) a carefully curated dataset of diverse objects and scenes captured under controlled lighting conditions. Together, these components enable efficient finetuning of pretrained diffusion models while also providing a solid benchmark for downstream evaluation. Experiments demonstrate that $\pi$-Light synthesizes specular highlights and diffuse reflections across a wide variety of materials, achieving superior generalization to real-world scenes compared with prior approaches.