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

arXiv: https://arxiv.org/abs/2601.22135 · HTML: https://mlsanity.com/paper/2601.22135/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 30 of its 42 references that are in the map.
- First posted on arXiv 29 Jan 2026.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 30 of 30)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [Objaverse-XL: A Universe of 10M+ 3D Objects](https://mlsanity.com/paper/2307.05663/) (2023)
- [Wonder3D: Single Image to 3D using Cross-Domain Diffusion](https://mlsanity.com/paper/2310.15008/) (2023)
- [GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image](https://mlsanity.com/paper/2403.12013/) (2024)
- [Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF from a Single Image](https://mlsanity.com/paper/1905.02722/) (2019)
- [RGBleftrightarrowX: Image decomposition and synthesis using material- and lighting-aware diffusion models](https://mlsanity.com/paper/2405.00666/) (2024)
- [Rethinking Inductive Biases for Surface Normal Estimation](https://mlsanity.com/paper/2403.00712/) (2024)
- [Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation](https://mlsanity.com/paper/2109.09881/) (2021)
- [DiLightNet: Fine-grained Lighting Control for Diffusion-based Image Generation](https://mlsanity.com/paper/2402.11929/) (2024)
- [Neural Gaffer: Relighting Any Object via Diffusion](https://mlsanity.com/paper/2406.07520/) (2024)
- [Learning-based Inverse Rendering of Complex Indoor Scenes with Differentiable Monte Carlo Raytracing](https://mlsanity.com/paper/2211.03017/) (2022)
- [Intrinsic Image Diffusion for Indoor Single-view Material Estimation](https://mlsanity.com/paper/2312.12274/) (2023)
- [IntrinsicAnything: Learning Diffusion Priors for Inverse Rendering Under Unknown Illumination](https://mlsanity.com/paper/2404.11593/) (2024)
- [Do 2D GANs Know 3D Shape? Unsupervised 3D shape reconstruction from 2D Image GANs](https://mlsanity.com/paper/2011.00844/) (2020)
- [LightIt: Illumination Modeling and Control for Diffusion Models](https://mlsanity.com/paper/2403.10615/) (2024)
- [DreamMat: High-quality PBR Material Generation with Geometry- and Light-aware Diffusion Models](https://mlsanity.com/paper/2405.17176/) (2024)
- [A Diffusion Approach to Radiance Field Relighting using Multi-Illumination Synthesis](https://mlsanity.com/paper/2409.08947/) (2024)
- [DifFRelight: Diffusion-Based Facial Performance Relighting](https://mlsanity.com/paper/2410.08188/) (2024)
- [Relightify: Relightable 3D Faces from a Single Image via Diffusion Models](https://mlsanity.com/paper/2305.06077/) (2023)
- [OutCast: Outdoor Single-image Relighting with Cast Shadows](https://mlsanity.com/paper/2204.09341/) (2022)
- [IllumiNeRF: 3D Relighting Without Inverse Rendering](https://mlsanity.com/paper/2406.06527/) (2024)
- [ScribbleLight: Single Image Indoor Relighting with Scribbles](https://mlsanity.com/paper/2411.17696/) (2024)
- [Relighting Humans in the Wild: Monocular Full-Body Human Relighting with Domain Adaptation](https://mlsanity.com/paper/2110.07272/) (2021)
- [MAIR: Multi-view Attention Inverse Rendering with 3D Spatially-Varying Lighting Estimation](https://mlsanity.com/paper/2303.12368/) (2023)
- [Controllable Light Diffusion for Portraits](https://mlsanity.com/paper/2305.04745/) (2023)
- [Diffusion Reflectance Map: Single-Image Stochastic Inverse Rendering of Illumination and Reflectance](https://mlsanity.com/paper/2312.04529/) (2023)
- [Lasagna: Layered Score Distillation for Disentangled Object Relighting](https://mlsanity.com/paper/2312.00833/) (2023)

## Built on by (most cited first, 5 of 5)

- [Generative World Renderer](https://mlsanity.com/paper/2604.02329/) (2026)
- [Do Image Editing Models Understand Lighting?](https://mlsanity.com/paper/2606.26738/) (2026)
- [FusionRelight: Relighting Portraits in Real Time via Hybrid Domain Knowledge Fusion](https://mlsanity.com/paper/2604.23094/) (2026)
- [RelightFormer: Feed-forward Generative Transformer for Multiview Object Relighting](https://mlsanity.com/paper/2609.07414/) (2026)
- [PhysReflect: Geometry and Perception Guided Diffusion for Physically-Plausible Mirror Reflections](https://mlsanity.com/paper/2609.23442/) (2026)

## Abstract (arXiv)

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 (π-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 π-Light synthesizes specular highlights and diffuse reflections across a wide variety of materials, achieving superior generalization to real-world scenes compared with prior approaches.