NLOS Imaging Survey · 2022 · Updated 2026

Recent Advances on Non-Line-of-Sight Imaging

Conventional Physical Models · Deep Learning · New Scenes

Ruixu Geng  ·  Yang Hu  ·  Yan Chen

What is NLOS Imaging?

Seeing around corners — reconstructing hidden scenes from multiply-scattered light

Non-Line-of-Sight (NLOS) imaging reconstructs hidden scenes that cannot be directly observed. Light emitted by a laser hits a visible relay surface (e.g., a wall), bounces into the hidden space, reflects off the hidden object, and returns to the relay surface where a sensor captures it. Computational algorithms then invert this light transport to recover the hidden scene.

NLOS imaging spans a rich diversity of hardware platforms (streak cameras, SPADs, ToF cameras, interferometers, radar, acoustic transducers), physical models (time-of-flight ellipsoidal models, wave-based phasor field models), and reconstruction algorithms (back-projection, LCT, f-k migration, deep learning, neural implicit representations).

Applications: autonomous driving, search-and-rescue, medical imaging, robotics, surveillance — anywhere seeing beyond the direct line of sight matters.

  [Laser / Detector]
        │
        │ ① 1st bounce (relay wall)
        ↓
  ┌─────────────────────┐
  │  Visible relay wall  │
  │  ② 2nd bounce ──►  Hidden │
  │          ◄── ③ 3rd bounce  Object│
  └─────────────────────┘
        │
        ↓ Measurement  τ(x, y, t)
  [Reconstruction Algorithm]
        │
        ↓ Hidden scene  ρ(x, y, z)
  FBP · LCT · f-k · Phasor Field
  Transformer · Mamba · GNN · Diffusion

Field at a Glance

Multi-dimensional statistics across 170+ papers (2008–2026) — all figures approximate

170+
Papers Surveyed
~72
Active NLOS
~32
Passive NLOS
~48
Deep Learning
~20
New NLOS Scenes
19
Years Covered
2008 – 2026
30+
Publication Venues
& Journals
5+
Physical Modalities
(optical, radar…)

Annual Publication Trend by Research Category

Stacked bars show how Active NLOS, Passive NLOS, Deep Learning, and New Scenes each grew year by year

Top Publication Venues

Distribution across leading optics, vision, and AI venues (selected major venues)

Research Task / Output

Primary goal of each paper — reconstruction, detection, tracking, or recognition (papers may span multiple tasks)

Sensor / Hardware Platform

Hardware diversity across surveyed papers; some papers use multiple sensor types

Deep Learning Architecture Types

Among ~48 deep-learning NLOS papers — how network design has diversified since 2018

Development History

Key milestones that shaped the NLOS Imaging field

2008

Raskar & Davis — "5D Time-Light Transport"

Theoretical foundation for transient NLOS imaging.

2012

Velten et al. — First Experimental 3D NLOS Reconstruction Nature Comm.

Streak camera + Filter Back Projection. Proved NLOS imaging is experimentally feasible.

2014

Heide et al. — "Diffuse Mirrors" SIGGRAPH

Low-cost ToF camera + TV optimization for NLOS imaging.

2015

Buttafava et al. — SPAD-Based NLOS

Demonstrated SPAD as an affordable alternative to streak cameras, democratizing the field.

2018

O'Toole et al. — Confocal NLOS + Light-Cone Transform (LCT) Nature

Reduced reconstruction from O(N⁵) to O(N³ log N). Landmark paper enabling real-time NLOS.

2018

Liu et al. — Phasor Field Virtual Wave Optics

Reformulated NLOS imaging as a virtual LOS diffraction problem, enabling new algorithms.

2019

Lindell et al. — f-k Migration (Wave-Based) SIGGRAPH

Applied seismic f-k migration to NLOS. Robust wave-based reconstruction at O(N³ log N).

2019

Saunders et al. — Computational Periscopy Nature

3D passive NLOS with an ordinary camera and partial occluder.

2020

Liu et al. — Phasor Field Diffraction SIGGRAPH

Extended phasor field to non-confocal NLOS settings with O(N³ log N) complexity.

2021

Wu et al. — 1.43 km Long-Range NLOS Nature Comm.

Extended NLOS imaging range from meters to 1.43 km — three orders of magnitude.

2021

Shen et al. — Neural Transient Field (NeTF) TPAMI

First unsupervised neural implicit field for NLOS — no paired training data required.

2022

Cao et al. — UNCOVER, Sub-mm NLOS Nature Photonics

Wavefront shaping achieves ~0.6 mm resolution at 0.55 m — 900× distance-to-resolution ratio.

2023

Li et al. — NLOST: First Transformer for NLOS CVPR

Spatial-temporal self-attention captures multi-scale correlations in 3D transient volumes.

2023

Wang et al. — PAC-Net + NLOS-Track Dataset CVPR

Real-time passive NLOS tracking; first large-scale dynamic passive NLOS dataset.

2023

Fujimura et al. — NLOS-NeuS: Neural Implicit Surface ICCV

SDF-based neural implicit surface reconstruction for smooth 3D NLOS geometry.

2024

Ye et al. — Real-Time 4 fps NLOS Video Nat. Comput. Sci.

Spectrum filtering + interleaved scanning achieves 4 fps NLOS video of room-sized dynamic scenes.

2024

Li et al. — ST-Mamba NeurIPS   Cui et al. — Virtual Scanning NeurIPS

First Mamba model for NLOS video (temporal consistency); unsupervised reconstruction from irregular undersampled transients.

2024

Czajkowski & Murray-Bruce — 3D Passive NLOS with Ordinary Camera Nature Comm.

Full-color 3D passive NLOS reconstruction requiring no calibration images.

2025

Li et al. — TransiT: 10 fps NLOS Video CVPR

64×64 NLOS video at 10 fps from 16×16 sparse transient inputs via transfer learning.

2025

Su et al. — DG-NLOS (GNN) AAAI   Sun et al. — Learnable Physical Priors CVPR

First GNN for NLOS reconstruction; learnable physical priors for generalization across diverse scene conditions.

2025

Lai et al. — HoloRadar: mmWave 3D NLOS NeurIPS

Full 3D NLOS scene reconstruction with a single mobile mmWave radar.

2026

New frontiers 2026

Human pose estimation (OLE), polarization single-pixel scanning-free NLOS (PRL), super-field-of-view imaging (Photonics Research).

Paper List

Key papers from the survey, organized by category. Filter or search below.

Datasets & Code

Open resources for NLOS Imaging research

LCT / f-k Confocal Dataset

Active confocal SPAD dataset from O'Toole et al. (Nature 2018) and Lindell et al. (SIGGRAPH 2019). Includes transient measurements of multiple 3D hidden objects.

↗ github.com/computational-imaging/nlos-fk

Galindo Benchmark

Benchmark dataset for time-resolved NLOS measurements, designed for systematic evaluation of reconstruction algorithms.

↗ doi.org/10.1364/OE.380140

NLOS-Track Dataset

First large-scale dynamic passive NLOS tracking dataset. Thousands of video clips with trajectory labels for evaluating passive NLOS tracking methods. (Wang et al., CVPR 2023)

Link via paper authors

1.43 km NLOS Imaging Code

Code and data for the long-range 1.43 km NLOS imaging system by Wu et al. (Nature Communications 2021).

↗ github.com/quantum-inspired-lidar/…

Acoustic NLOS Code

Code for acoustic NLOS imaging using microphone arrays (Lindell et al., SIGGRAPH 2019). Uses the same f-k migration framework as optical NLOS.

↗ github.com/computational-imaging/acoustic-nlos

NLOS Transient Renderer

The first dedicated NLOS transient renderer for generating realistic synthetic training data. (Royo et al., 2022)

Link via paper authors

Fast Differentiable Transient Renderer

Differentiable transient renderer supporting auto-differentiation for end-to-end NLOS network training. (Plack et al., 2023)

Link via paper authors

NLOS-Passive Dataset

Real passive NLOS measurement dataset captured with conventional cameras and ambient light, released alongside the optimal transport reconstruction paper (Geng et al., IEEE TIP 2022).

↗ github.com/ruixv/NLOS-OT

NLOS-OT Code

Optimal transport–based passive NLOS reconstruction code. Includes the NLOS-Passive dataset, OT solver, and evaluation scripts. (Geng et al., IEEE TIP 2022)

↗ github.com/ruixv/NLOS-OT

This Survey Repository

Comprehensive curated list of 150+ NLOS papers with categorization, timeline, and links. Contributions welcome.

↗ github.com/ruixv/NLOS_Overview