# Shedding Light: A Benchmark for Evaluating Lighting Understanding in Generative Image Models

arXiv: https://arxiv.org/abs/2609.10787 · HTML: https://mlsanity.com/paper/2609.10787/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 52 of its 97 references that are in the map.
- First posted on arXiv 9 Sep 2026.

## Builds on (most cited first, 30 of 52)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Blended Diffusion for Text-driven Editing of Natural Images](https://mlsanity.com/paper/2111.14818/) (2021)
- [Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation](https://mlsanity.com/paper/2008.00951/) (2020)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer](https://mlsanity.com/paper/2511.22699/) (2025)
- [Video models are zero-shot learners and reasoners](https://mlsanity.com/paper/2509.20328/) (2025)
- [Diffusion Model-Based Image Editing: A Survey](https://mlsanity.com/paper/2402.17525/) (2024)
- [Effectively Unbiased FID and Inception Score and where to find them](https://mlsanity.com/paper/1911.07023/) (2019)
- [Learning to Predict Indoor Illumination from a Single Image](https://mlsanity.com/paper/1704.00090/) (2017)
- [PieAPP: Perceptual Image-Error Assessment through Pairwise Preference](https://mlsanity.com/paper/1806.02067/) (2018)
- [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)
- [Image inpainting: A review](https://mlsanity.com/paper/1909.06399/) (2019)
- [Deep Parametric Indoor Lighting Estimation](https://mlsanity.com/paper/1910.08812/) (2019)
- [Learning Indoor Inverse Rendering with 3D Spatially-Varying Lighting](https://mlsanity.com/paper/2109.06061/) (2021)
- [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)
- [DeepLight: Learning Illumination for Unconstrained Mobile Mixed Reality](https://mlsanity.com/paper/1904.01175/) (2019)
- [I2EBench: A Comprehensive Benchmark for Instruction-based Image Editing](https://mlsanity.com/paper/2408.14180/) (2024)

## Built on by (most cited first, 1 of 1)

- [The Camera Inside the Editor: Reading the Implicit Camera of Image Editors with Painted Calibration Patterns](https://mlsanity.com/paper/2609.37732/) (2026)

## Abstract (arXiv)

Accurate modelling of illumination is central to realistic image synthesis and scene understanding. Yet, there is little exploration into whether image generative models are good at this task or whether physical plausibility remains a key challenge for them. Clearly, significant progress has been made in realistic image synthesis, but do models truly understand lighting in a physically accurate manner? To answer this question, this work proposes a benchmark to assess the lighting understanding and harmonisation capabilities of generative models. Our key insight is that evaluating lighting understanding for such models only requires testing how well they insert novel objects into real photographs whilst maintaining consistent illumination. To do so, we use a multi-illumination dataset with images containing simple objects serving as ``light probes'', and prompt models to inpaint the same object onto the original image, then compare the generated results against the ground-truth light probes. We then estimate the lighting direction, colour and radiance distribution from the inpainted probes, providing a quantitative measure of illumination accuracy and photometric realism. Our work establishes a scalable evaluation protocol to systematically assess how well generative models capture and reproduce real-world lighting, offering a foundation for benchmarking the photometric accuracy of any future models. All code and data are available at https://lvsn.github.io/SheddingLight/ .