# Neural Inverse Rendering from Propagating Light

arXiv: https://arxiv.org/abs/2506.05347 · HTML: https://mlsanity.com/paper/2506.05347/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 95 references that are in the map.
- First posted on arXiv 5 Jun 2025.

## Builds on (most cited first, 30 of 42)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Learning Implicit Fields for Generative Shape Modeling](https://mlsanity.com/paper/1812.02822/) (2018)
- [Depth-supervised NeRF: Fewer Views and Faster Training for Free](https://mlsanity.com/paper/2107.02791/) (2021)
- [Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields](https://mlsanity.com/paper/2304.06706/) (2023)
- [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)
- [NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images](https://mlsanity.com/paper/2111.13679/) (2021)
- [Urban Radiance Fields](https://mlsanity.com/paper/2111.14643/) (2021)
- [Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition](https://mlsanity.com/paper/2110.14373/) (2021)
- [Modeling Indirect Illumination for Inverse Rendering](https://mlsanity.com/paper/2204.06837/) (2022)
- [TensoIR: Tensorial Inverse Rendering](https://mlsanity.com/paper/2304.12461/) (2023)
- [NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images](https://mlsanity.com/paper/2305.17398/) (2023)
- [3D Gaussian Ray Tracing: Fast Tracing of Particle Scenes](https://mlsanity.com/paper/2407.07090/) (2024)
- [NeILF: Neural Incident Light Field for Physically-based Material Estimation](https://mlsanity.com/paper/2203.07182/) (2022)
- [Lidar for Autonomous Driving: The principles, challenges, and trends for automotive lidar and perception systems](https://mlsanity.com/paper/2004.08467/) (2020)
- [SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collections](https://mlsanity.com/paper/2205.15768/) (2022)
- [T"oRF: Time-of-Flight Radiance Fields for Dynamic Scene View Synthesis](https://mlsanity.com/paper/2109.15271/) (2021)
- [Neural LiDAR Fields for Novel View Synthesis](https://mlsanity.com/paper/2305.01643/) (2023)
- [Virtual Wave Optics for Non-Line-of-Sight Imaging](https://mlsanity.com/paper/1810.07535/) (2018)
- [NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fields](https://mlsanity.com/paper/2304.14811/) (2023)
- [Non-line-of-sight Imaging](https://mlsanity.com/paper/2005.08026/) (2020)
- [NeFII: Inverse Rendering for Reflectance Decomposition with Near-Field Indirect Illumination](https://mlsanity.com/paper/2303.16617/) (2023)
- [Neural Microfacet Fields for Inverse Rendering](https://mlsanity.com/paper/2303.17806/) (2023)
- [Volume Rendering Digest (for NeRF)](https://mlsanity.com/paper/2209.02417/) (2022)
- [Transient Neural Radiance Fields for Lidar View Synthesis and 3D Reconstruction](https://mlsanity.com/paper/2307.09555/) (2023)
- [Non-Line-of-Sight Reconstruction using Efficient Transient Rendering](https://mlsanity.com/paper/1809.08044/) (2018)
- [Towards 3D Vision with Low-Cost Single-Photon Cameras](https://mlsanity.com/paper/2403.17801/) (2024)
- [Seeing Around Corners with Edge-Resolved Transient Imaging](https://mlsanity.com/paper/2002.07118/) (2020)
- [Flash Cache: Reducing Bias in Radiance Cache Based Inverse Rendering](https://mlsanity.com/paper/2409.05867/) (2024)

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

- [PhaSR: Generalized Image Shadow Removal with Physically Aligned Priors](https://mlsanity.com/paper/2601.17470/) (2026)

## Abstract (arXiv)

We present the first system for physically based, neural inverse rendering from multi-viewpoint videos of propagating light. Our approach relies on a time-resolved extension of neural radiance caching -- a technique that accelerates inverse rendering by storing infinite-bounce radiance arriving at any point from any direction. The resulting model accurately accounts for direct and indirect light transport effects and, when applied to captured measurements from a flash lidar system, enables state-of-the-art 3D reconstruction in the presence of strong indirect light. Further, we demonstrate view synthesis of propagating light, automatic decomposition of captured measurements into direct and indirect components, as well as novel capabilities such as multi-view time-resolved relighting of captured scenes.