# Propagate And Calibrate: Real-time Passive Non-line-of-sight Tracking

arXiv: https://arxiv.org/abs/2303.11791 · HTML: https://mlsanity.com/paper/2303.11791/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 48 references that are in the map.
- First posted on arXiv 21 Mar 2023.

## Builds on (most cited first, 19 of 19)

- [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)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series](https://mlsanity.com/paper/1905.12374/) (2019)
- [Virtual Wave Optics for Non-Line-of-Sight Imaging](https://mlsanity.com/paper/1810.07535/) (2018)
- [Non-line-of-sight Imaging](https://mlsanity.com/paper/2005.08026/) (2020)
- [Recent Advances in Imaging Around Corners](https://mlsanity.com/paper/1910.05613/) (2019)
- [Keyhole Imaging: Non-Line-of-Sight Imaging and Tracking of Moving Objects Along a Single Optical Path](https://mlsanity.com/paper/1912.06727/) (2019)
- [Two-Dimensional Non-Line-of-Sight Scene Estimation from a Single Edge Occluder](https://mlsanity.com/paper/2006.09241/) (2020)
- [Non-line-of-sight tracking of people at long range](https://mlsanity.com/paper/1703.02124/) (2017)
- [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)
- [Optically lightweight tracking of objects around a corner](https://mlsanity.com/paper/1606.01873/) (2016)
- [Neural network identification of people hidden from view with a single-pixel, single-photon detector](https://mlsanity.com/paper/1709.07244/) (2017)
- [Flash Photography for Data-Driven Hidden Scene Recovery](https://mlsanity.com/paper/1810.11710/) (2018)
- [Passive Non-line-of-sight Imaging for Moving Targets with an Event Camera](https://mlsanity.com/paper/2209.13300/) (2022)

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

- [PathFinder: Attention-Driven Dynamic Non-Line-of-Sight Tracking with a Mobile Robot](https://mlsanity.com/paper/2404.05024/) (2024)
- [TransiT: Transient Transformer for Non-line-of-sight Videography](https://mlsanity.com/paper/2503.11328/) (2025)

## Abstract (arXiv)

Non-line-of-sight (NLOS) tracking has drawn increasing attention in recent years, due to its ability to detect object motion out of sight. Most previous works on NLOS tracking rely on active illumination, e.g., laser, and suffer from high cost and elaborate experimental conditions. Besides, these techniques are still far from practical application due to oversimplified settings. In contrast, we propose a purely passive method to track a person walking in an invisible room by only observing a relay wall, which is more in line with real application scenarios, e.g., security. To excavate imperceptible changes in videos of the relay wall, we introduce difference frames as an essential carrier of temporal-local motion messages. In addition, we propose PAC-Net, which consists of alternating propagation and calibration, making it capable of leveraging both dynamic and static messages on a frame-level granularity. To evaluate the proposed method, we build and publish the first dynamic passive NLOS tracking dataset, NLOS-Track, which fills the vacuum of realistic NLOS datasets. NLOS-Track contains thousands of NLOS video clips and corresponding trajectories. Both real-shot and synthetic data are included. Our codes and dataset are available at https://againstentropy.github.io/NLOS-Track/.