Research map / 3D vision / Depth and stereo
Snapshot hyperspectral imaging
Reconstructs spectral images from coded or dispersive snapshots with learned or physics-guided models.
38 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 Checklist 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.
8 papers in 2023–24 and 9 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 2.6% to 2.2%.
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 · Do It Yourself Hyperspectral Imaging With Everyday Digital Cameras (CVPR 2016 · 81 citations)
- 2017 · What Is the Space of Attenuation Coefficients in Underwater Computer Vision? (CVPR 2017 · 201 citations)
- 2018 · Deeply Learned Filter Response Functions for Hyperspectral Reconstruction (CVPR 2018 · 99 citations)
- 2019 · Dichromatic Model Based Temporal Color Constancy for AC Light Sources (CVPR 2019 · 22 citations)
- 2020 · Plug-and-Play Algorithms for Large-Scale Snapshot Compressive Imaging (CVPR 2020 · 202 citations)
- 2021 · Deep Gaussian Scale Mixture Prior for Spectral Compressive Imaging (CVPR 2021 · 170 citations)
- 2022 · Degree-of-Linear-Polarization-Based Color Constancy (CVPR 2022 · 26 citations)
- 2023 · Residual Degradation Learning Unfolding Framework With Mixing Priors Across Spectral and Spatial for Compressive Spectral Imaging (CVPR 2023 · 66 citations)
- 2024 · Dispersed Structured Light for Hyperspectral 3D Imaging (CVPR 2024 · 14 citations)
- 2025 · Active Hyperspectral Imaging Using an Event Camera (CVPR 2025 · 9 citations)
- 2026 · Spectrum from Defocus: Fast Spectral Imaging with Chromatic Focal Stack (CVPR 2026 · 1 citation)
Earliest papers here
- Do It Yourself Hyperspectral Imaging With Everyday Digital Cameras (CVPR 2016 · 81 citations)
- Simultaneous Estimation of Near IR BRDF and Fine-Scale Surface Geometry (CVPR 2016 · 19 citations)
- What Is the Space of Attenuation Coefficients in Underwater Computer Vision? (CVPR 2017 · 201 citations)
What has been tried
33 papers here report 268 measured changes (a component added, removed or swapped, compared with a baseline): helped 80%, no clear effect 4%, hurt 15%, mixed 1%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| add first-order diffraction to the reconstruction | Nine 10 nm bandpass filters · spectral FWHM | 50 nm -> 18.8 nm | Helped | Dispersed Structured Light for Hyperspectral 3D Imaging (CVPR 2024 · 14 citations) |
| Add CRW | KAIST simulated, average · PSNR | 37.23 -> 40.05 (+2.82 dB) | Helped | In2SET: Intra-Inter Similarity Exploiting Transformer for Dual-Camera Compressive Hyperspectral Imaging (CVPR 2024 · 12 citations) |
| Add centroid-matching loss | LSMI Galaxy · illuminant number accuracy (# acc.) | 0.288 -> 0.800 | Helped | Attentive Illumination Decomposition Model for Multi-Illuminant White Balancing (CVPR 2024 · 11 citations) |
| add non-negative constraints | Spectral reconstruction · SAM | 30.23 -> 13.42 | Helped | Active Hyperspectral Imaging Using an Event Camera (CVPR 2025 · 9 citations) |
| Add the first stage to a second-stage-only network | Pavia center · PSNR | 38.0810 -> 38.8193 | Helped | FMPM-DNet: Hyperspectral Pansharpening Dynamic Network Based on Feature Modulation and Probability Mask (AAAI 2025 · 4 citations) |
| use adaptive sampling instead of uniform sampling | Set11, 10% sampling · PSNR | 30.24 -> 31.05 | Helped | Reconstruction-free Cascaded Adaptive Compressive Sensing (CVPR 2024 · 4 citations) |
| Set loffset to 60 instead of the chosen 40 | DDSL pattern parameter ablation · spectral FWHM [nm] | 15.5 -> 15.5 | No clear effect | Dense Dispersed Structured Light for Hyperspectral 3D Imaging of Dynamic Scenes (CVPR 2025 · 3 citations) |
| Train with natural-image sampling instead of uniform sampling | Natural images · mean ΔE | 2.44{\scriptstyle ±0.03} -> 1.09{\scriptstyle ±0.01} | Helped | Efficient Neural Network Encoding for 3D Color Lookup Tables (AAAI 2025 · 0 citations) |
| add intensity-guided mask | KAIST simulation · PSNR | 35.77 -> 40.83 | Helped | Spectral Compressive Imaging via Chromaticity-Intensity Decomposition (NeurIPS 2025 · 0 citations) |
What reviewers will expect
Datasets and baselines named in the 5 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- ColorChecker chart · 2 of 5 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 17 papers; from OpenAlex and the papers' affiliations).
- Samsung · 2 papers
Use it
Download BibTeX of 30 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)
- Non-line-of-sight imaging (93 papers)
- Spike and event camera reconstruction (50 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).