Research map / Architectures and efficiency / Attention and transformers
Image Content Matters: An Image Content Aware State Space Model for Accelerated MRI Reconstruction
Yucong Meng, Zhiwei Yang, Kexue Fu, Zhijian Song, Yonghong Shi
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 SPSM instead of SS2D scanning (ablation) | CAM · CC359 (brain), AF=4 ablation | PSNR (dB): 38.20 -> 39.37 | Improved |
| add TESM texture sequence (ablation) | CAM · CC359 (brain), AF=4 ablation | PSNR (dB): 38.30 -> 39.37 | Improved |
| add TEMM texture injection (ablation) | CAM · CC359 (brain), AF=4 ablation | PSNR (dB): 38.43 -> 39.37 | Improved |
| add KSMM k-space module (ablation) | CAM · CC359 (brain), AF=4 ablation | PSNR (dB): 39.15 -> 39.37 | Improved |
| learnable centers instead of Kmeans in SPSM (ablation) | CAM · CC359 (brain), AF=4 ablation | PSNR (dB): 38.79 -> 39.37 | Improved |
| add center contrastive loss Lcon (ablation) | CAM · CC359 (brain), AF=4 ablation | PSNR (dB): 39.02 -> 39.37 | Improved |
| use learned texture instead of random noise sequence (ablation) | CAM · CC359 (brain), AF=4 ablation | PSNR (dB): 35.71 -> 39.37 | Improved |
| increase semantic centers K from 2 to 6 (ablation) | CAM · CC359 (brain), AF=4 ablation | PSNR (dB): 38.36 -> 39.37 | Improved |
| increase K beyond 6 (ablation) | CAM · CC359 (brain), AF=4 ablation | PSNR (dB): 39.37 -> 39.20 | Hurt |
| inject texture into A, B and C of the SSM (ablation) | CAM · CC359 (brain), AF=4 ablation | PSNR (dB): 37.36 -> 39.37 | Improved |
| CAM versus best prior on SKM-TEA AF=4 | CAM · SKM-TEA AF=4 | PSNR (dB): 35.64 -> 35.66 | Improved |
Closest papers by meaning
- MambaIRv2: Attentive State Space Restoration (CVPR 2025 · similarity 0.87)
- MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration (CVPR 2025 · similarity 0.86)
- 2DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classification (CVPR 2025 · similarity 0.86)
- Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion (ICLR 2025 · similarity 0.86)
- LC-Mamba: Local and Continuous Mamba with Shifted Windows for Frame Interpolation (CVPR 2025 · similarity 0.85)
- Boosting ViT-based MRI Reconstruction from the Perspectives of Frequency Modulation, Spatial Purification, and Scale Diversification (AAAI 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.
