# DiffusionLight-Turbo: Accelerated Light Probes for Free via Single-Pass Chrome Ball Inpainting

arXiv: https://arxiv.org/abs/2507.01305 · HTML: https://mlsanity.com/paper/2507.01305/

## Key facts

- Cited by 12 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 49 of its 74 references that are in the map.
- First posted on arXiv 2 Jul 2025.

## 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 49)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [Blended Diffusion for Text-driven Editing of Natural Images](https://mlsanity.com/paper/2111.14818/) (2021)
- [Pseudo Numerical Methods for Diffusion Models on Manifolds](https://mlsanity.com/paper/2202.09778/) (2022)
- [Paint by Example: Exemplar-based Image Editing with Diffusion Models](https://mlsanity.com/paper/2211.13227/) (2022)
- [UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models](https://mlsanity.com/paper/2302.04867/) (2023)
- [Blended Latent Diffusion](https://mlsanity.com/paper/2206.02779/) (2022)
- [SVDiff: Compact Parameter Space for Diffusion Fine-Tuning](https://mlsanity.com/paper/2303.11305/) (2023)
- [P+: Extended Textual Conditioning in Text-to-Image Generation](https://mlsanity.com/paper/2303.09522/) (2023)
- [Controlling Text-to-Image Diffusion by Orthogonal Finetuning](https://mlsanity.com/paper/2306.07280/) (2023)
- [Learning to Predict Indoor Illumination from a Single Image](https://mlsanity.com/paper/1704.00090/) (2017)
- [ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Content](https://mlsanity.com/paper/1803.02266/) (2018)
- [Deep Parametric Indoor Lighting Estimation](https://mlsanity.com/paper/1910.08812/) (2019)
- [Learning-based Inverse Rendering of Complex Indoor Scenes with Differentiable Monte Carlo Raytracing](https://mlsanity.com/paper/2211.03017/) (2022)
- [Fast Spatially-Varying Indoor Lighting Estimation](https://mlsanity.com/paper/1906.03799/) (2019)
- [Rendering Synthetic Objects into Legacy Photographs](https://mlsanity.com/paper/1912.11565/) (2019)
- [Deep Sky Modeling for Single Image Outdoor Lighting Estimation](https://mlsanity.com/paper/1905.03897/) (2019)
- [DiffusionLight: Light Probes for Free by Painting a Chrome Ball](https://mlsanity.com/paper/2312.09168/) (2023)
- [DeepLight: Learning Illumination for Unconstrained Mobile Mixed Reality](https://mlsanity.com/paper/1904.01175/) (2019)

## Built on by (most cited first, 12 of 12)

- [UniLight: A Unified Representation for Lighting](https://mlsanity.com/paper/2512.04267/) (2025)
- [Lighting in Motion: Spatiotemporal HDR Lighting Estimation](https://mlsanity.com/paper/2512.13597/) (2025)
- [Lighting-grounded Video Generation with Renderer-based Agent Reasoning](https://mlsanity.com/paper/2604.07966/) (2026)
- [Generalizable Sparse-View 3D Reconstruction from Unconstrained Images](https://mlsanity.com/paper/2604.28193/) (2026)
- [Do Image Editing Models Understand Lighting?](https://mlsanity.com/paper/2606.26738/) (2026)
- [Video Generation Models Are Inherent Lighting Estimators](https://mlsanity.com/paper/2607.04674/) (2026)
- [Shedding Light: A Benchmark for Evaluating Lighting Understanding in Generative Image Models](https://mlsanity.com/paper/2609.10787/) (2026)
- [CFSR: Geometry-Conditioned Shadow Removal via Physical Disentanglement](https://mlsanity.com/paper/2604.18032/) (2026)
- [PIXLRelight: Controllable Relighting via Intrinsic Conditioning](https://mlsanity.com/paper/2605.18735/) (2026)
- [BRDFusion: Physics Meets Generation for Urban Scene Inverse Rendering](https://mlsanity.com/paper/2606.17049/) (2026)
- [Diffusion-Based Material Regularization for Physics-Based Inverse Rendering](https://mlsanity.com/paper/2606.31065/) (2026)
- [LAMP: 3D Source-Aware Lighting Estimation at Multiple Points](https://mlsanity.com/paper/2610.19266/) (2026)

## Abstract (arXiv)

We introduce a simple yet effective technique for estimating lighting from a single low-dynamic-range (LDR) image by reframing the task as a chrome ball inpainting problem. This approach leverages a pre-trained diffusion model, Stable Diffusion XL, to overcome the generalization failures of existing methods that rely on limited HDR panorama datasets. While conceptually simple, the task remains challenging because diffusion models often insert incorrect or inconsistent content and cannot readily generate chrome balls in HDR format. Our analysis reveals that the inpainting process is highly sensitive to the initial noise in the diffusion process, occasionally resulting in unrealistic outputs. To address this, we first introduce DiffusionLight, which uses iterative inpainting to compute a median chrome ball from multiple outputs to serve as a stable, low-frequency lighting prior that guides the generation of a high-quality final result. To generate high-dynamic-range (HDR) light probes, an Exposure LoRA is fine-tuned to create LDR images at multiple exposure values, which are then merged. While effective, DiffusionLight is time-intensive, requiring approximately 30 minutes per estimation. To reduce this overhead, we introduce DiffusionLight-Turbo, which reduces the runtime to about 30 seconds with minimal quality loss. This 60x speedup is achieved by training a Turbo LoRA to directly predict the averaged chrome balls from the iterative process. Inference is further streamlined into a single denoising pass using a LoRA swapping technique. Experimental results that show our method produces convincing light estimates across diverse settings and demonstrates superior generalization to in-the-wild scenarios. Our code is available at https://diffusionlight.github.io/turbo