Research map / 3D vision / Depth and stereo
Deep Gaussian Scale Mixture Prior for Spectral Compressive Imaging
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use learned GSM scale priors and local means in the MAP reconstruction network | HSI reconstruction from CASSI measurements · KAIST test (10 scenes), average | PSNR (dB): 31.46 -> 32.63 | Helped |
| Use learned GSM scale priors and local means in the MAP reconstruction network | HSI reconstruction from CASSI measurements · KAIST test (10 scenes), average | SSIM: 0.8939 -> 0.9166 | Helped |
| Train one model on a compound dataset with five masks using learned measurement operations | DGSM-SCI · KAIST test (10 scenes), five masks | PSNR: mask1: 30.96 -> 31.38; mask2: 31.23 -> 31.73; mask3: 31.43 -> 31.81; mask4: 31.15 -> 31.58; mask5: 31.46 -> 31.70 | Helped |
| Add dense connections (ablation) | DGSM-SCI · KAIST test (10 scenes) | PSNR (dB): 30.52dB -> 32.63dB | Helped |
| Add dense connections (ablation) | DGSM-SCI · KAIST test (10 scenes) | SSIM: 0.8802 -> 0.9166 | Helped |
| Increase the spatial-spectral filter size (ablation) | DGSM-SCI · HSI reconstruction simulation | reconstruction quality | Helped |
| Increase the number of reconstruction stages (ablation) | DGSM-SCI · HSI reconstruction simulation | reconstruction performance | Helped |
| Use average pooling instead of max pooling (ablation) | DGSM-SCI U-Net · HSI reconstruction | reconstruction performance | Helped |
| Use bilinear interpolation in decoder blocks (ablation) | DGSM-SCI U-Net · HSI reconstruction | reconstruction performance | Helped |
Closest papers by meaning
- Dual-Window Multiscale Transformer for Hyperspectral Snapshot Compressive Imaging (AAAI 2024 · similarity 0.89)
- Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms (NeurIPS 2024 · similarity 0.88)
- Spectral Compressive Imaging via Chromaticity-Intensity Decomposition (NeurIPS 2025 · similarity 0.87)
- Sp3ctralMamba: Physics-Driven Joint State Space Model for Hyperspectral Image Reconstruction (AAAI 2025 · similarity 0.87)
- HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models (CVPR 2024 · similarity 0.87)
- Detail Matters: Mamba-Inspired Joint Unfolding Network for Snapshot Spectral Compressive Imaging (AAAI 2025 · similarity 0.87)
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.