Research map / 3D vision / Depth and stereo
l-Net: Reconstruct Hyperspectral Images From a Snapshot Measurement
Xin Miao, Xin Yuan, Yunchen Pu, Vassilis Athitsos
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add GAN (ablation) | lambda-net · MIL simulation average | PSNR: 29.48 -> 32.29 | Improved |
| add self-attention (ablation) | lambda-net · MIL simulation average | PSNR: 28.77 -> 32.29 | Improved |
| add refinement stage (ablation) | lambda-net · MIL simulation average | PSNR: 30.67 -> 32.29 | Improved |
| add hierarchical channel reconstruction (HCR) (ablation) | lambda-net · MIL simulation average | PSNR: 31.81 -> 32.29 | Improved |
| add residual learning in refinement U-net (ablation) | lambda-net · MIL simulation average | PSNR: 31.02 -> 32.29 | Improved |
| feed masks along with the measurement (ablation) | lambda-net · MIL simulation average | PSNR: 30.20 -> 32.29 | Improved |
| use deeper U-net instead of original U-net (ablation) | lambda-net · MIL simulation average | PSNR: 30.37 -> 32.29 | Improved |
| use lambda-net instead of DeSCI | lambda-net · MIL simulation average | PSNR: 27.62 -> 32.29 | Improved |
| use lambda-net instead of DeSCI on Scene 4 (simple scene with large white area) | lambda-net · MIL Scene 4 | PSNR: 29.78 -> 28.90 | Hurt |
| use lambda-net instead of DeSCI on real bird data | lambda-net · Real bird data | PSNR: 25.13 -> 25.59 | Improved |
| use lambda-net instead of other deep networks | lambda-net · Simulation average | PSNR: 29.07 -> 32.29 | Improved |
Closest papers by meaning
- Effective Snapshot Compressive-Spectral Imaging via Deep Denoising and Total Variation Priors (CVPR 2021 · similarity 0.91)
- HerosNet: Hyperspectral Explicable Reconstruction and Optimal Sampling Deep Network for Snapshot Compressive Imaging (CVPR 2022 · similarity 0.91)
- FRN: Fractal-Based Recursive Spectral Reconstruction Network (NeurIPS 2025 · similarity 0.90)
- Spectral Compressive Imaging via Chromaticity-Intensity Decomposition (NeurIPS 2025 · similarity 0.90)
- SPECAT: SPatial-spEctral Cumulative-Attention Transformer for High-Resolution Hyperspectral Image Reconstruction (CVPR 2024 · similarity 0.89)
- Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms (NeurIPS 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
