# Real-time Non-line-of-Sight imaging of dynamic scenes

arXiv: https://arxiv.org/abs/2010.12737 · HTML: https://mlsanity.com/paper/2010.12737/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Oct 2020.

## Built on by (most cited first, 20 of 20)

- [Physics to the Rescue: Deep Non-line-of-sight Reconstruction for High-speed Imaging](https://mlsanity.com/paper/2205.01679/) (2022)
- [Few-shot Non-line-of-sight Imaging with Signal-surface Collaborative Regularization](https://mlsanity.com/paper/2211.15367/) (2022)
- [Omni-Line-of-Sight Imaging for Holistic Shape Reconstruction](https://mlsanity.com/paper/2304.10780/) (2023)
- [Virtual Mirrors: Non-Line-of-Sight Imaging Beyond the Third Bounce](https://mlsanity.com/paper/2307.14341/) (2023)
- [Self-Calibrating, Fully Differentiable NLOS Inverse Rendering](https://mlsanity.com/paper/2309.12047/) (2023)
- [Learning to Enhance Aperture Phasor Field for Non-Line-of-Sight Imaging](https://mlsanity.com/paper/2407.18574/) (2024)
- [Large-scale single-photon imaging](https://mlsanity.com/paper/2212.13654/) (2022)
- [Curvature regularization for Non-line-of-sight Imaging from Under-sampled Data](https://mlsanity.com/paper/2301.00406/) (2023)
- [Synthetic Wavelength Imaging -- Utilizing Spectral Correlations for High-Precision Time-of-Flight Sensing](https://mlsanity.com/paper/2209.04941/) (2022)
- [Domain Reduction Strategy for Non Line of Sight Imaging](https://mlsanity.com/paper/2308.10269/) (2023)
- [MARMOT: Masked Autoencoder for Modeling Transient Imaging](https://mlsanity.com/paper/2506.08470/) (2025)
- [Noise-adapted Neural Operator for Robust Non-Line-of-Sight Imaging](https://mlsanity.com/paper/2508.09655/) (2025)
- [A comprehensive study of time-of-flight non-line-of-sight imaging](https://mlsanity.com/paper/2603.09548/) (2026)
- [Non-line-of-sight imaging in the presence of scattering media using phasor fields](https://mlsanity.com/paper/2311.09223/) (2023)
- [Iterating the Transient Light Transport Matrix for Non-Line-of-Sight Imaging](https://mlsanity.com/paper/2412.10300/) (2024)
- [Dual-branch Graph Feature Learning for NLOS Imaging](https://mlsanity.com/paper/2502.19683/) (2025)
- [TransiT: Transient Transformer for Non-line-of-sight Videography](https://mlsanity.com/paper/2503.11328/) (2025)
- [Geometric Constrained Non-Line-of-Sight Imaging](https://mlsanity.com/paper/2503.17992/) (2025)
- [Imaging Hidden Objects with Consumer LiDAR via Motion Induced Sampling](https://mlsanity.com/paper/2605.17865/) (2026)
- [Memory-efficient GPU pipelines for real-time non-line-of-sight reconstruction](https://mlsanity.com/paper/2608.28183/) (2026)

## Abstract (arXiv)

Non-Line-of-Sight (NLOS) imaging aims at recovering the 3D geometry of objects that are hidden from the direct line of sight. In the past, this method has suffered from the weak available multibounce signal limiting scene size, capture speed, and reconstruction quality. While algorithms capable of reconstructing scenes at several frames per second have been demonstrated, real-time NLOS video has only been demonstrated for retro-reflective objects where the NLOS signal strength is enhanced by 4 orders of magnitude or more. Furthermore, it has also been noted that the signal-to-noise ratio of reconstructions in NLOS methods drops quickly with distance and past reconstructions, therefore, have been limited to small scenes with depths of few meters. Actual models of noise and resolution in the scene have been simplistic, ignoring many of the complexities of the problem. We show that SPAD (Single-Photon Avalanche Diode) array detectors with a total of just 28 pixels combined with a specifically extended Phasor Field reconstruction algorithm can reconstruct live real-time videos of non-retro-reflective NLOS scenes. We provide an analysis of the Signal-to-Noise-Ratio (SNR) of our reconstructions and show that for our method it is possible to reconstruct the scene such that SNR, motion blur, angular resolution, and depth resolution are all independent of scene size suggesting that reconstruction of very large scenes may be possible. In the future, the light efficiency for NLOS imaging systems can be improved further by adding more pixels to the sensor array.