# Computational Mirrors: Blind Inverse Light Transport by Deep Matrix Factorization

arXiv: https://arxiv.org/abs/1912.02314 · HTML: https://mlsanity.com/paper/1912.02314/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Dec 2019.

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

- [DeepTensor: Low-Rank Tensor Decomposition with Deep Network Priors](https://mlsanity.com/paper/2204.03145/) (2022)
- [Recent Advances on Non-Line-of-Sight Imaging: Conventional Physical Models, Deep Learning, and New Scenes](https://mlsanity.com/paper/2104.13807/) (2021)
- [What You Can Learn by Staring at a Blank Wall](https://mlsanity.com/paper/2108.13027/) (2021)
- [Neural Global Shutter: Learn to Restore Video from a Rolling Shutter Camera with Global Reset Feature](https://mlsanity.com/paper/2204.00974/) (2022)
- [Totems: Physical Objects for Verifying Visual Integrity](https://mlsanity.com/paper/2209.13032/) (2022)
- [Non-Line-of-Sight Tracking and Mapping with an Active Corner Camera](https://mlsanity.com/paper/2208.01702/) (2022)
- [Can Shadows Reveal Biometric Information?](https://mlsanity.com/paper/2209.10077/) (2022)
- [Domain Reduction Strategy for Non Line of Sight Imaging](https://mlsanity.com/paper/2308.10269/) (2023)
- [Fast Non-line-of-sight Imaging with Two-step Deep Remapping](https://mlsanity.com/paper/2101.10492/) (2021)
- [Passive Non-Line-of-Sight Imaging with Light Transport Modulation](https://mlsanity.com/paper/2312.16014/) (2023)
- [PathFinder: Attention-Driven Dynamic Non-Line-of-Sight Tracking with a Mobile Robot](https://mlsanity.com/paper/2404.05024/) (2024)
- [Soft Shadow Diffusion (SSD): Physics-inspired Learning for 3D Computational Periscopy](https://mlsanity.com/paper/2601.12257/) (2026)

## Abstract (arXiv)

We recover a video of the motion taking place in a hidden scene by observing changes in indirect illumination in a nearby uncalibrated visible region. We solve this problem by factoring the observed video into a matrix product between the unknown hidden scene video and an unknown light transport matrix. This task is extremely ill-posed, as any non-negative factorization will satisfy the data. Inspired by recent work on the Deep Image Prior, we parameterize the factor matrices using randomly initialized convolutional neural networks trained in a one-off manner, and show that this results in decompositions that reflect the true motion in the hidden scene.