Research map / Video / Video segmentation and tracking
Large Motion Video Super-Resolution with Dual Subnet and Multi-Stage Communicated Upsampling
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 DSMC instead of the strongest PSNR baseline DBPN | VSR on REDS4 · REDS4 | PSNR: 25.28 -> 25.73 | Helped |
| Use DSMC instead of the strongest SSIM baseline FRVSR | VSR on REDS4 · REDS4 | SSIM: 0.8256 -> 0.8428 | Helped |
| Use DSMC instead of 3DSRnet | VSR on Vid4 · Vid4 | PSNR: 24.37 -> 24.63 | Helped |
| Use DSMC instead of 3DSRnet | VSR on Vid4 · Vid4 | SSIM: 0.8262 -> 0.8403 | Helped |
| Add MSCU to the DSMC architecture (ablation) | DSMC · REDS validation clips | PSNR: 20.48 -> 25.73 | Helped |
| Add the MSCU ResNet feature-correction submodule (ablation) | DSMC MSCU · REDS validation clips | PSNR: 24.81 -> 25.73 | Helped |
| Add MSCU communication (ablation) | DSMC MSCU · REDS validation clips | PSNR: 22.30 -> 25.73 | Helped |
| Add MSCU ResNet feature correction and communication (ablation) | DSMC MSCU · REDS validation clips | PSNR: 21.77 -> 25.73 | Helped |
| Add U3D-RDN (ablation) | DSMC · REDS validation clips | PSNR: 22.64 -> 25.73 | Helped |
| Add the U3D-RDN non-local layer (ablation) | DSMC U3D-RDN · REDS validation clips | PSNR: 25.59 -> 25.73 | Helped |
| Add dual Cb loss to Cb loss in the VSR subnet (ablation) | DSMC · REDS validation clips | PSNR: 25.70 -> 25.71 | Helped |
| Add matching dual Cb and perceptual losses (ablation) | DSMC · REDS validation clips | PSNR: 25.67 -> 25.73 | Helped |
Closest papers by meaning
- Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation (CVPR 2018 · similarity 0.94)
- Video Face Super-Resolution with Motion-Adaptive Feedback Cell (AAAI 2020 · similarity 0.90)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.89)
- Arbitrary-Scale Video Super-resolution Guided by Dynamic Context (AAAI 2024 · similarity 0.87)
- FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurring (CVPR 2024 · similarity 0.86)
- VideoGigaGAN: Towards Detail-rich Video Super-Resolution (CVPR 2025 · similarity 0.86)
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.