Research map / 3D vision / Depth and stereo
Non-line-of-sight imaging
Reconstructs hidden or transparent geometry from time-of-flight light transport.
93 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Depth and stereo, keyword cluster “light · imaging · illumination”
State History Tried Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
27 papers in 2023–24 and 20 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 8.8% to 4.9%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2016 · 3D Reconstruction of Transparent Objects With Position-Normal Consistency (CVPR 2016 · 69 citations)
- 2017 · The Geometry of First-Returning Photons for Non-Line-Of-Sight Imaging (CVPR 2017 · 74 citations)
- 2018 · Deep End-to-End Time-of-Flight Imaging (CVPR 2018 · 108 citations)
- 2019 · Light Field Messaging With Deep Photographic Steganography (CVPR 2019 · 162 citations)
- 2020 · Non-Line-of-Sight Surface Reconstruction Using the Directional Light-Cone Transform (CVPR 2020 · 59 citations)
- 2021 · Panoramic Image Reflection Removal (CVPR 2021 · 25 citations)
- 2022 · Shape From Polarization for Complex Scenes in the Wild (CVPR 2022 · 69 citations)
- 2023 · Event-Based Shape From Polarization (CVPR 2023 · 36 citations)
- 2024 · Towards 3D Vision with Low-Cost Single-Photon Cameras (CVPR 2024 · 13 citations)
- 2025 · Event Ellipsometer: Event-based Mueller-Matrix Video Imaging (CVPR 2025 · 6 citations)
- 2026 · Physically-Guided Optical Inversion Enable Non-Contact Side-Channel Attack on Isolated Screens (ICLR 2026 · 0 citations)
Earliest papers here
- 3D Reconstruction of Transparent Objects With Position-Normal Consistency (CVPR 2016 · 69 citations)
- Recovering Transparent Shape From Time-Of-Flight Distortion (CVPR 2016 · 40 citations)
- Macroscopic Interferometry: Rethinking Depth Estimation With Frequency-Domain Time-Of-Flight (CVPR 2016 · 32 citations)
What has been tried
77 papers here report 543 measured changes (a component added, removed or swapped, compared with a baseline): helped 76%, no clear effect 4%, hurt 17%, mixed 3%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Use the joint image-frame and event-stack measurement instead of image-only acquisition | BasicLFSR test (ALL) · PSNR | 26.85 -> 33.79 | Helped | Time-Efficient Light-Field Acquisition Using Coded Aperture and Events (CVPR 2024 · 10 citations) |
| add the virtual scanning process | Simulated complex-geometry transients, 15 relay surfaces · PSNR | 19.63 -> 20.52 | Helped | Virtual Scanning: Unsupervised Non-line-of-sight Imaging from Irregularly Undersampled Transients (NeurIPS 2024 · 10 citations) |
| Use four polarization images instead of one | Our real-world dataset · mean angular error (°) | 19.46 -> 15.73 | Helped | SfPUEL: Shape from Polarization under Unknown Environment Light (NeurIPS 2024 · 8 citations) |
| use the full reconstruction pipeline instead of SVD initialization alone | Synthetic scene · reconstruction error | 0.11 -> 0.04 | Helped | Event Ellipsometer: Event-based Mueller-Matrix Video Imaging (CVPR 2025 · 6 citations) |
| Increase the thermal-video duration | Color chart · albedo error | Mixed | A Theory of Joint Light and Heat Transport for Lambertian Scenes (CVPR 2024 · 5 citations) | |
| Add polarized information and the Polarization-based Location Model | Film Removal · PSNR | Helped | Learning to Remove Wrinkled Transparent Film with Polarized Prior (CVPR 2024 · 5 citations) | |
| use diffuse LiDAR loss instead of sparse point LiDAR loss | Rendered scenes · Depth MAE | 0.078 -> 0.041; 0.099 -> 0.040; 0.084 -> 0.036; 0.074 -> 0.037 | Helped | Blurred LiDAR for Sharper 3D: Robust Handheld 3D Scanning with Diffuse LiDAR and RGB (CVPR 2025 · 3 citations) |
| Add polarization information to wavefront and Mueller inputs | Synthetic data · mean angular error | 9.47 -> 8.71 | Helped | Polarization Wavefront Lidar: Learning Large Scene Reconstruction from Polarized Wavefronts (CVPR 2024 · 3 citations) |
| add graph selection to the baseline | Ablation study · PSNR | 28.37 -> 28.68 | Helped | Dual-branch Graph Feature Learning for NLOS Imaging (AAAI 2025 · 2 citations) |
| Add polarization cues to rendering | RedOx · PSNR | 26.29 -> 30.88 | Helped | Glossy Object Reconstruction with Cost-effective Polarized Acquisition (CVPR 2025 · 2 citations) |
| Replace max pooling with mean pooling | TrShape, hexahedron · PSNR | 37.41 -> 35.53 | Hurt | Practical Measurements of Translucent Materials with Inter-Pixel Translucency Prior (CVPR 2024 · 2 citations) |
| add radial weight w2 to RVL | MG, IRSG, UTSG, EGB · PSNR | MG: 22.498 (2.578) -> 24.206 (2.547); IRSG: 24.435 (2.577) -> 26.540 (2.653); UTSG: 23.477 (2.574) -> 25.430 (2.565); EG | Helped | PolarRec: Improving Radio Interferometric Data Reconstruction Using Polar Coordinates (CVPR 2024 · 1 citation) |
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 47 papers; from OpenAlex and the papers' affiliations).
- University of Science and Technology of China · 4 papers
- Massachusetts Institute of Technology · 3 papers
- Zhejiang University · 2 papers
- Stanford University · 2 papers
- Hong Kong University of Science and Technology · 2 papers
- Pohang University of Science and Technology · 2 papers
Use it
Download BibTeX of 40 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Neural light field and illumination imaging (107 papers)
- Spike and event camera reconstruction (50 papers)
- Snapshot hyperspectral imaging (38 papers)
Elsewhere in the topic
- Feed-forward 3D reconstruction (133 papers)
- Self-supervised monocular depth (116 papers)
- Scene coordinate regression for localization (112 papers)
- Learned optical and scene flow (108 papers)
- Cost-volume multi-view stereo (107 papers)
- Camera model and calibration for SfM (99 papers)
- Dense depth prediction and completion (85 papers)
- Foundation models for monocular geometry (81 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).