Research map / 3D vision / Depth and stereo
Efficient Snapshot Spectral Imaging: Calibration-Free Parallel Structure with Aperture Diffraction Fusion
Tao Lv, Lihao Hu, Shiqiao Li, Chenglong Huang, Xun Cao
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 RGB prior branch (MAD+RGB) instead of RGB only (ablation) | SSFCT decoder · CAVE-trained SSFCT-5stg | PSNR (dB): 35.53 -> 36.33 | Improved |
| add self-aware feature encoding module (SFEM) (ablation) | SSFCT · CAVE-trained SSFCT-5stg | PSNR (dB): 36.33 -> 36.76 | Improved |
| add alignment loss L_align to the reconstruction loss (ablation) | SSFCT · CAVE-trained SSFCT-5stg | PSNR (dB): 36.76 -> 37.38 | Improved |
| use SSFCT instead of Restormer for uncalibrated inputs | PCCADIS · KAIST uncalibrated simulation | PSNR (dB): 39.48 -> 41.33 | Improved |
| switch from serial ADIS coding to parallel PCCADIS with SSFCT (uncalibrated) | snapshot spectral imaging system · KAIST simulation | PSNR (dB): 34.08 -> 41.33 | Improved |
| parallel architecture gives higher light throughput than serial ADIS | PCCADIS · light throughput analysis | Light throughput: 8.3% -> 29.2% (Mm); 25.0% -> 54.2% (Mc) | Improved |
| use uncalibrated input rather than perfectly calibrated input with SSFCT | PCCADIS · KAIST simulation | PSNR (dB): 41.97 (WC, CSST) vs 41.33 (UC, SSFCT) | Hurt |
| vary mask period d (dispersion parameter) | PCCADIS · well-calibrated simulation | PSNR (dB) | No clear effect |
Closest papers by meaning
- Aperture Diffraction for Compact Snapshot Spectral Imaging (ICCV 2023 · similarity 0.91)
- From Local to Global: A Progressive Reconstruction Network for Diffractive Snapshot Spectral Imaging (ECCV 2026 · similarity 0.89)
- Prior Image Guided Snapshot Compressive Spectral Imaging (TPAMI 2023 · similarity 0.87)
- Aperture-aware Dispersion 5-D Light-field Imaging Spectrometer (TPAMI 2026 · similarity 0.87)
- Spectral Compressive Imaging via Chromaticity-Intensity Decomposition (NeurIPS 2025 · similarity 0.85)
- SPECAT: SPatial-spEctral Cumulative-Attention Transformer for High-Resolution Hyperspectral Image Reconstruction (CVPR 2024 · similarity 0.83)
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.
