Research map / Video / Video segmentation and tracking
MedVSR: Medical Video Super-Resolution with Cross State-Space Propagation
Xinyu Liu, Guolei Sun, Cheng Wang, Yixuan Yuan, Ender Konukoglu
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 MedVSR (CSSP + ISSR) instead of best baseline VSRT | medical VSR · HyperKvasir | PSNR: 31.7789 -> 32.0958 | Improved |
| use MedVSR instead of BasicVSR++ on surgical scenes | medical VSR · EndoVis18 | PSNR: 30.7977 -> 30.8344 | No clear effect |
| add learnable position embedding (LPE) in CSSB (ablation) | MedVSR · HyperKvasir | PSNR: 31.8102 -> 32.0958 | Improved |
| add local windows (LW) in CSSB (ablation) | MedVSR · HyperKvasir | PSNR: 31.8201 -> 32.0958 | Improved |
| use separate projection layers for the distant and neighbor frames in CSSB (ablation) | MedVSR · HyperKvasir | PSNR: 31.7386 -> 32.0958 | Improved |
| add local windows in ISSB (ablation) | MedVSR · HyperKvasir | PSNR: 31.8215 -> 32.0958 | Improved |
| use concatenation instead of gating in ISSB (ablation) | MedVSR · HyperKvasir | PSNR: 31.8528 -> 32.0958 | Improved |
| use large-kernel separable block 7x7 instead of ResBlock (ablation) | MedVSR reconstruction · HyperKvasir | PSNR: 31.8067 -> 32.0958 | Improved |
| increase LKSB kernel size from 7 to 9 (ablation) | MedVSR · HyperKvasir | PSNR: 32.0958 -> 31.8852 | Hurt |
| use distant frame t-2 to support frame t-1 instead of propagating only t-1 to t (ablation) | CSSP · HyperKvasir | PSNR: 31.7734 -> 32.0958 | Improved |
| increase local window size from 16 to 32 (ablation) | MedVSR · HyperKvasir | PSNR: 32.0958 -> 31.8366 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- BasicVSR++ — BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond (CVPR 2021) · better on 4 of 5 shared results
- TCNet — TCNet: Continuous Sign Language Recognition from Trajectories and Correlated Regions (AAAI 2024) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- MedGSSR: Generalizable Medical Image Super-Resolution 3D Reconstruction via Hierarchical Feed-forward Gaussian Splatting (ECCV 2026 · similarity 0.87)
- Sequence Matters: Harnessing Video Models in 3D Super-Resolution (AAAI 2025 · similarity 0.86)
- BF-STVSR: B-Splines and Fourier---Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution (CVPR 2025 · similarity 0.84)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.84)
- CycleINR: Cycle Implicit Neural Representation for Arbitrary-Scale Volumetric Super-Resolution of Medical Data (CVPR 2024 · similarity 0.84)
- Block-Based Multi-Scale Image Rescaling (AAAI 2025 · similarity 0.84)
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.
