Research map / 3D vision / Depth and stereo
Residual Degradation Learning Unfolding Framework With Mixing Priors Across Spectral and Spatial for Compressive Spectral Imaging
Read the paperCheck 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 RDLUF-MixS² with 9 stages instead of DAUHST-9stg | CASSI HSI reconstruction · KAIST 10-scene average | PSNR (dB): +1.21 dB | Helped |
| Add residual degradation learning to the spectral-branch baseline (ablation) | RDLUF-MixS² · KAIST ablation evaluation | PSNR (dB): +0.61 | Helped |
| Add a spatial branch (ablation) | RDLUF-MixS² with residual degradation learning · KAIST ablation evaluation | PSNR (dB): +0.20 | Helped |
| Add bi-directional interaction across spectral and spatial branches (ablation) | RDLUF-MixS² · KAIST ablation evaluation | PSNR (dB): +0.11 | Helped |
| Add block interaction (ablation) | RDLUF-MixS² · KAIST ablation evaluation | PSNR (dB): +0.09 | Helped |
| Add stage interaction (ablation) | RDLUF-MixS² · KAIST ablation evaluation | PSNR (dB): +0.06 | Helped |
| Increase the number of stages from 3 to 9 (ablation) | RDLUF-MixS² · KAIST 10-scene average | PSNR (dB): 37.56 -> 39.57 | Helped |
| Use independent parameters across all 9 stages instead of shared parameters (ablation) | RDLUF-MixS² · KAIST 10-scene average | PSNR (dB): 39.57 -> 39.03 | Hurt |
Closest papers by meaning
- Spectral Compressive Imaging via Chromaticity-Intensity Decomposition (NeurIPS 2025 · similarity 0.88)
- Detail Matters: Mamba-Inspired Joint Unfolding Network for Snapshot Spectral Compressive Imaging (AAAI 2025 · similarity 0.87)
- Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms (NeurIPS 2024 · similarity 0.85)
- DiffSCI: Zero-Shot Snapshot Compressive Imaging via Iterative Spectral Diffusion Model (CVPR 2024 · similarity 0.85)
- SSUN-Net: Spatial-Spectral Prior-Aware Unfolding Network for Pan-Sharpening (AAAI 2025 · similarity 0.85)
- Dual-Window Multiscale Transformer for Hyperspectral Snapshot Compressive Imaging (AAAI 2024 · similarity 0.85)
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.