# Spatially-Varying Outdoor Lighting Estimation from Intrinsics

arXiv: https://arxiv.org/abs/2104.04160 · HTML: https://mlsanity.com/paper/2104.04160/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 27 references that are in the map.
- First posted on arXiv 9 Apr 2021.

## Builds on (most cited first, 18 of 18)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [Semantic Scene Completion from a Single Depth Image](https://mlsanity.com/paper/1611.08974/) (2016)
- [Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF from a Single Image](https://mlsanity.com/paper/1905.02722/) (2019)
- [Learning to Predict Indoor Illumination from a Single Image](https://mlsanity.com/paper/1704.00090/) (2017)
- [InverseRenderNet: Learning single image inverse rendering](https://mlsanity.com/paper/1811.12328/) (2018)
- [Fast Spatially-Varying Indoor Lighting Estimation](https://mlsanity.com/paper/1906.03799/) (2019)
- [Deep Sky Modeling for Single Image Outdoor Lighting Estimation](https://mlsanity.com/paper/1905.03897/) (2019)
- [DeepLight: Learning Illumination for Unconstrained Mobile Mixed Reality](https://mlsanity.com/paper/1904.01175/) (2019)
- [Neural Illumination: Lighting Prediction for Indoor Environments](https://mlsanity.com/paper/1906.07370/) (2019)
- [Deep Outdoor Illumination Estimation](https://mlsanity.com/paper/1611.06403/) (2016)
- [All-Weather Deep Outdoor Lighting Estimation](https://mlsanity.com/paper/1906.04909/) (2019)
- [Physically-Based Rendering for Indoor Scene Understanding Using Convolutional Neural Networks](https://mlsanity.com/paper/1612.07429/) (2016)
- [Learning High Dynamic Range from Outdoor Panoramas](https://mlsanity.com/paper/1703.10200/) (2017)
- [Im2Pano3D: Extrapolating 360 Structure and Semantics Beyond the Field of View](https://mlsanity.com/paper/1712.04569/) (2017)

## Built on by (most cited first, 14 of 14)

- [Neural Fields meet Explicit Geometric Representation for Inverse Rendering of Urban Scenes](https://mlsanity.com/paper/2304.03266/) (2023)
- [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)
- [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)
- [Factorized and Controllable Neural Re-Rendering of Outdoor Scene for Photo Extrapolation](https://mlsanity.com/paper/2207.06899/) (2022)
- [360 Depth Estimation in the Wild -- The Depth360 Dataset and the SegFuse Network](https://mlsanity.com/paper/2202.08010/) (2022)
- [LuxDiT: Lighting Estimation with Video Diffusion Transformer](https://mlsanity.com/paper/2509.03680/) (2025)
- [UniLight: A Unified Representation for Lighting](https://mlsanity.com/paper/2512.04267/) (2025)
- [Creating a Forensic Database of Shoeprints from Online Shoe Tread Photos](https://mlsanity.com/paper/2205.02361/) (2022)
- [Spatio-Temporal Outdoor Lighting Aggregation on Image Sequences using Transformer Networks](https://mlsanity.com/paper/2202.09206/) (2022)
- [Lighting in Motion: Spatiotemporal HDR Lighting Estimation](https://mlsanity.com/paper/2512.13597/) (2025)
- [StylePart: Image-based Shape Part Manipulation](https://mlsanity.com/paper/2111.10520/) (2021)

## Abstract (arXiv)

We present SOLID-Net, a neural network for spatially-varying outdoor lighting estimation from a single outdoor image for any 2D pixel location. Previous work has used a unified sky environment map to represent outdoor lighting. Instead, we generate spatially-varying local lighting environment maps by combining global sky environment map with warped image information according to geometric information estimated from intrinsics. As no outdoor dataset with image and local lighting ground truth is readily available, we introduce the SOLID-Img dataset with physically-based rendered images and their corresponding intrinsic and lighting information. We train a deep neural network to regress intrinsic cues with physically-based constraints and use them to conduct global and local lightings estimation. Experiments on both synthetic and real datasets show that SOLID-Net significantly outperforms previous methods.