Research map / Image generation / Super-resolution
MambaX: Image Super-Resolution With State Predictive Control
Chenyu Li, Danfeng Hong, Bing Zhang, Zhaojie Pan, Naoto Yokoya, Jocelyn Chanussot
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 |
|---|---|---|---|
| use nonlinear state predictive control instead of linear control matrices (ablation) | MambaX · Gaofen II | PSNR (dB): 43.12 -> 43.65 | Improved |
| add spatial operator S_l to control matrix generation (ablation) | MambaX · Gaofen II | PSNR (dB): 43.52 -> 43.65 | Improved |
| add spectral operator C_l to control matrix generation (ablation) | MambaX · Gaofen II | PSNR (dB): 43.50 -> 43.65 | Improved |
| make all control variables dynamic rather than linear (ablation) | MambaX · WV3/GF2 | PSNR | Mixed |
| use progressive cross-domain transition instead of bicubic upsampling (ablation) | MambaX · Pavia (x2) | PSNR (dB): 35.18 -> 35.43 | Improved |
| use progressive cross-domain transition instead of PixelShuffle (ablation) | MambaX · Pavia (x2) | PSNR (dB): 35.24 -> 35.43 | Improved |
| add adaptive fusion weights to the transition (ablation) | MambaX · Pavia (x2) | PSNR (dB): 35.37 -> 35.43 | Improved |
| generate B from auxiliary image S (cross-control) instead of from X only (ablation) | MambaX · WorldView III | PSNR (dB): 37.34 -> 37.87 | Improved |
| generate C from S instead of B from S (ablation) | MambaX · WorldView III | PSNR (dB): 37.87 -> 37.75 | Hurt |
Closest papers by meaning
- MambaIRv2: Attentive State Space Restoration (CVPR 2025 · similarity 0.86)
- Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion (ICLR 2025 · similarity 0.86)
- SinSR: Diffusion-Based Image Super-Resolution in a Single Step (CVPR 2024 · similarity 0.86)
- Detail Matters: Mamba-Inspired Joint Unfolding Network for Snapshot Spectral Compressive Imaging (AAAI 2025 · similarity 0.85)
- Noise-Free Optimization in Early Training Steps for Image Super-resolution (AAAI 2024 · similarity 0.85)
- TSP-Mamba: The Travelling Salesman Problem Meets Mamba for Image Super-resolution and Beyond (CVPR 2025 · 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.
