# Generalizable Non-Line-of-Sight Imaging with Learnable Physical Priors

arXiv: https://arxiv.org/abs/2409.14011 · HTML: https://mlsanity.com/paper/2409.14011/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 33 references that are in the map.
- First posted on arXiv 21 Sep 2024.

## Builds on (most cited first, 11 of 11)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Virtual Wave Optics for Non-Line-of-Sight Imaging](https://mlsanity.com/paper/1810.07535/) (2018)
- [Seeing Around Street Corners: Non-Line-of-Sight Detection and Tracking In-the-Wild Using Doppler Radar](https://mlsanity.com/paper/1912.06613/) (2019)
- [Fast Back-Projection for Non-Line of Sight Reconstruction](https://mlsanity.com/paper/1703.02016/) (2017)
- [Deep Non-Line-of-Sight Reconstruction](https://mlsanity.com/paper/2001.09067/) (2020)
- [Recent Advances in Imaging Around Corners](https://mlsanity.com/paper/1910.05613/) (2019)
- [Physics to the Rescue: Deep Non-line-of-sight Reconstruction for High-speed Imaging](https://mlsanity.com/paper/2205.01679/) (2022)
- [A Computational Model of a Single-Photon Avalanche Diode Sensor for Transient Imaging](https://mlsanity.com/paper/1703.02635/) (2017)
- [Learning to Enhance Aperture Phasor Field for Non-Line-of-Sight Imaging](https://mlsanity.com/paper/2407.18574/) (2024)

## Built on by (most cited first, 2 of 2)

- [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)

## Abstract (arXiv)

Non-line-of-sight (NLOS) imaging, recovering the hidden volume from indirect reflections, has attracted increasing attention due to its potential applications. Despite promising results, existing NLOS reconstruction approaches are constrained by the reliance on empirical physical priors, e.g., single fixed path compensation. Moreover, these approaches still possess limited generalization ability, particularly when dealing with scenes at a low signal-to-noise ratio (SNR). To overcome the above problems, we introduce a novel learning-based solution, comprising two key designs: Learnable Path Compensation (LPC) and Adaptive Phasor Field (APF). The LPC applies tailored path compensation coefficients to adapt to different objects in the scene, effectively reducing light wave attenuation, especially in distant regions. Meanwhile, the APF learns the precise Gaussian window of the illumination function for the phasor field, dynamically selecting the relevant spectrum band of the transient measurement. Experimental validations demonstrate that our proposed approach, only trained on synthetic data, exhibits the capability to seamlessly generalize across various real-world datasets captured by different imaging systems and characterized by low SNRs.