# Deep Outdoor Illumination Estimation

arXiv: https://arxiv.org/abs/1611.06403 · HTML: https://mlsanity.com/paper/1611.06403/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2016.

## Built on by (most cited first, 30 of 53)

- [Editable Scene Simulation for Autonomous Driving via Collaborative LLM-Agents](https://mlsanity.com/paper/2402.05746/) (2024)
- [Neural Fields meet Explicit Geometric Representation for Inverse Rendering of Urban Scenes](https://mlsanity.com/paper/2304.03266/) (2023)
- [Learning Indoor Inverse Rendering with 3D Spatially-Varying Lighting](https://mlsanity.com/paper/2109.06061/) (2021)
- [DiffusionLight: Light Probes for Free by Painting a Chrome Ball](https://mlsanity.com/paper/2312.09168/) (2023)
- [StyleLight: HDR Panorama Generation for Lighting Estimation and Editing](https://mlsanity.com/paper/2207.14811/) (2022)
- [Free-viewpoint Indoor Neural Relighting from Multi-view Stereo](https://mlsanity.com/paper/2106.13299/) (2021)
- [Self-supervised Outdoor Scene Relighting](https://mlsanity.com/paper/2107.03106/) (2021)
- [Deep Learning for HDR Imaging: State-of-the-Art and Future Trends](https://mlsanity.com/paper/2110.10394/) (2021)
- [Deep Learning for Omnidirectional Vision: A Survey and New Perspectives](https://mlsanity.com/paper/2205.10468/) (2022)
- [ObjectStitch: Generative Object Compositing](https://mlsanity.com/paper/2212.00932/) (2022)
- [Neural Light Field Estimation for Street Scenes with Differentiable Virtual Object Insertion](https://mlsanity.com/paper/2208.09480/) (2022)
- [EverLight: Indoor-Outdoor Editable HDR Lighting Estimation](https://mlsanity.com/paper/2304.13207/) (2023)
- [Single-image Full-body Human Relighting](https://mlsanity.com/paper/2107.07259/) (2021)
- [OutCast: Outdoor Single-image Relighting with Cast Shadows](https://mlsanity.com/paper/2204.09341/) (2022)
- [GMLight: Lighting Estimation via Geometric Distribution Approximation](https://mlsanity.com/paper/2102.10244/) (2021)
- [Photorealistic Object Insertion with Diffusion-Guided Inverse Rendering](https://mlsanity.com/paper/2408.09702/) (2024)
- [A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision](https://mlsanity.com/paper/2502.10444/) (2025)
- [LightSim: Neural Lighting Simulation for Urban Scenes](https://mlsanity.com/paper/2312.06654/) (2023)
- [IRIS: Inverse Rendering of Indoor Scenes from Low Dynamic Range Images](https://mlsanity.com/paper/2401.12977/) (2024)
- [Sparse Needlets for Lighting Estimation with Spherical Transport Loss](https://mlsanity.com/paper/2106.13090/) (2021)
- [Spatially-Varying Outdoor Lighting Estimation from Intrinsics](https://mlsanity.com/paper/2104.04160/) (2021)
- [Eclipse: Disambiguating Illumination and Materials using Unintended Shadows](https://mlsanity.com/paper/2305.16321/) (2023)
- [Point2Pix: Photo-Realistic Point Cloud Rendering via Neural Radiance Fields](https://mlsanity.com/paper/2303.16482/) (2023)
- [DiffusionLight-Turbo: Accelerated Light Probes for Free via Single-Pass Chrome Ball Inpainting](https://mlsanity.com/paper/2507.01305/) (2025)
- [GT-Loc: Unifying When and Where in Images Through a Joint Embedding Space](https://mlsanity.com/paper/2507.10473/) (2025)
- [Inverse Rendering of Translucent Objects using Physical and Neural Renderers](https://mlsanity.com/paper/2305.08336/) (2023)
- [GCC: Generative Color Constancy via Diffusing a Color Checker](https://mlsanity.com/paper/2502.17435/) (2025)
- [A Deep Perceptual Measure for Lens and Camera Calibration](https://mlsanity.com/paper/2208.12300/) (2022)
- [Repopulating Street Scenes](https://mlsanity.com/paper/2103.16183/) (2021)
- [Deep Graph Learning for Spatially-Varying Indoor Lighting Prediction](https://mlsanity.com/paper/2202.06300/) (2022)

## Abstract (arXiv)

We present a CNN-based technique to estimate high-dynamic range outdoor illumination from a single low dynamic range image. To train the CNN, we leverage a large dataset of outdoor panoramas. We fit a low-dimensional physically-based outdoor illumination model to the skies in these panoramas giving us a compact set of parameters (including sun position, atmospheric conditions, and camera parameters). We extract limited field-of-view images from the panoramas, and train a CNN with this large set of input image--output lighting parameter pairs. Given a test image, this network can be used to infer illumination parameters that can, in turn, be used to reconstruct an outdoor illumination environment map. We demonstrate that our approach allows the recovery of plausible illumination conditions and enables photorealistic virtual object insertion from a single image. An extensive evaluation on both the panorama dataset and captured HDR environment maps shows that our technique significantly outperforms previous solutions to this problem.