# MAIR: Multi-view Attention Inverse Rendering with 3D Spatially-Varying Lighting Estimation

arXiv: https://arxiv.org/abs/2303.12368 · HTML: https://mlsanity.com/paper/2303.12368/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 57 references that are in the map.
- First posted on arXiv 22 Mar 2023.

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://mlsanity.com/paper/2111.11215/) (2021)
- [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021)
- [Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields](https://mlsanity.com/paper/2112.03907/) (2021)
- [NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis](https://mlsanity.com/paper/2012.03927/) (2020)
- [NeRD: Neural Reflectance Decomposition from Image Collections](https://mlsanity.com/paper/2012.03918/) (2020)
- [PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting](https://mlsanity.com/paper/2104.00674/) (2021)
- [Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF from a Single Image](https://mlsanity.com/paper/1905.02722/) (2019)
- [Modeling Indirect Illumination for Inverse Rendering](https://mlsanity.com/paper/2204.06837/) (2022)
- [Modulating early visual processing by language](https://mlsanity.com/paper/1707.00683/) (2017)
- [Learning to Predict Indoor Illumination from a Single Image](https://mlsanity.com/paper/1704.00090/) (2017)
- [NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illumination](https://mlsanity.com/paper/2106.01970/) (2021)
- [Single-Image SVBRDF Capture with a Rendering-Aware Deep Network](https://mlsanity.com/paper/1810.09718/) (2018)
- [InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset](https://mlsanity.com/paper/1809.00716/) (2018)
- [CGIntrinsics: Better Intrinsic Image Decomposition through Physically-Based Rendering](https://mlsanity.com/paper/1808.08601/) (2018)
- [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)
- [Learning-based Inverse Rendering of Complex Indoor Scenes with Differentiable Monte Carlo Raytracing](https://mlsanity.com/paper/2211.03017/) (2022)
- [OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets](https://mlsanity.com/paper/2007.12868/) (2020)
- [Fast Spatially-Varying Indoor Lighting Estimation](https://mlsanity.com/paper/1906.03799/) (2019)
- [Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Image](https://mlsanity.com/paper/1804.05790/) (2018)
- [Lighthouse: Predicting Lighting Volumes for Spatially-Coherent Illumination](https://mlsanity.com/paper/2003.08367/) (2020)
- [Inverse Path Tracing for Joint Material and Lighting Estimation](https://mlsanity.com/paper/1903.07145/) (2019)
- [Physically-Based Editing of Indoor Scene Lighting from a Single Image](https://mlsanity.com/paper/2205.09343/) (2022)
- [IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenes](https://mlsanity.com/paper/2206.08423/) (2022)

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

- [Intrinsic Image Diffusion for Indoor Single-view Material Estimation](https://mlsanity.com/paper/2312.12274/) (2023)
- [ZeroComp: Zero-shot Object Compositing from Image Intrinsics via Diffusion](https://mlsanity.com/paper/2410.08168/) (2024)
- [Materialist: Physically Based Editing Using Single-Image Inverse Rendering](https://mlsanity.com/paper/2501.03717/) (2025)
- [MVInverse: Feed-forward Multi-view Inverse Rendering in Seconds](https://mlsanity.com/paper/2512.21003/) (2025)
- [PI-Light: Physics-Inspired Diffusion for Full-Image Relighting](https://mlsanity.com/paper/2601.22135/) (2026)
- [MAIR++: Improving Multi-view Attention Inverse Rendering with Implicit Lighting Representation](https://mlsanity.com/paper/2408.06707/) (2024)
- [Channel-wise Noise Scheduled Diffusion for Inverse Rendering in Indoor Scenes](https://mlsanity.com/paper/2503.09993/) (2025)
- [SAIL: Self-supervised Albedo Estimation from Real Images with a Latent Diffusion Model](https://mlsanity.com/paper/2505.19751/) (2025)
- [Yesnt: Are Diffusion Relighting Models Ready for Capture Stage Compositing? A Hybrid Alternative to Bridge the Gap](https://mlsanity.com/paper/2510.23494/) (2025)
- [IPCD: Intrinsic Point-Cloud Decomposition](https://mlsanity.com/paper/2511.09866/) (2025)
- [An evaluation of SVBRDF Prediction from Generative Image Models for Appearance Modeling of 3D Scenes](https://mlsanity.com/paper/2512.13950/) (2025)
- [PhysEditBench: A Protocol-Conditioned Benchmark for Dense Physical-Map Prediction with Image Editors](https://mlsanity.com/paper/2605.13493/) (2026)

## Abstract (arXiv)

We propose a scene-level inverse rendering framework that uses multi-view images to decompose the scene into geometry, a SVBRDF, and 3D spatially-varying lighting. Because multi-view images provide a variety of information about the scene, multi-view images in object-level inverse rendering have been taken for granted. However, owing to the absence of multi-view HDR synthetic dataset, scene-level inverse rendering has mainly been studied using single-view image. We were able to successfully perform scene-level inverse rendering using multi-view images by expanding OpenRooms dataset and designing efficient pipelines to handle multi-view images, and splitting spatially-varying lighting. Our experiments show that the proposed method not only achieves better performance than single-view-based methods, but also achieves robust performance on unseen real-world scene. Also, our sophisticated 3D spatially-varying lighting volume allows for photorealistic object insertion in any 3D location.