Research map / Video / Video segmentation and tracking
Memory-Augmented Non-Local Attention for Video Super-Resolution
Check 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 |
|---|---|---|---|
| Add memory-augmented attention (ablation) | MANA · Parkour dataset | PSNR (dB): 33.31 -> 33.48 | Helped |
| Add memory-augmented attention (ablation) | MANA · Vimeo90K dataset | PSNR (dB): 34.47 -> 34.71 | Helped |
| Add memory-augmented attention (ablation) | MANA · Vid4 dataset | PSNR (dB): 25.09 -> 25.15 | Helped |
| Add memory-augmented attention (ablation) | MANA · SPMC dataset | PSNR (dB): 29.03 -> 29.22 | Helped |
| Use memory size N=128 instead of N=256 (ablation) | MANA · Parkour dataset | PSNR (dB): 33.48 -> 33.44 | Hurt |
| Use memory size N=512 instead of N=256 (ablation) | MANA · Parkour dataset | PSNR (dB): 33.48 -> 33.47 | No clear effect |
| Use memory size N=1024 instead of N=256 (ablation) | MANA · Parkour dataset | PSNR (dB): 33.48 -> 33.47 | No clear effect |
| Use cross-frame non-local attention without frame alignment | MANA · Top 6% large-motion Vimeo90K videos | PSNR: 38.33 -> 38.62 | Helped |
| Use MANA instead of EDVR | Video super-resolution · Vimeo90K dataset | PSNR (dB): 35.68 -> 34.71 | Hurt |
| Use MANA instead of EDVR | Video super-resolution · Vid4 dataset | PSNR (dB): 25.79 -> 25.15 | Hurt |
Closest papers by meaning
- Video Super-Resolution With Temporal Group Attention (CVPR 2020 · similarity 0.91)
- EvEnhancer: Empowering Effectiveness, Efficiency and Generalizability for Continuous Space-Time Video Super-Resolution with Events (CVPR 2025 · similarity 0.88)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.88)
- One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution (NeurIPS 2025 · similarity 0.87)
- Learning Spatial Adaptation and Temporal Coherence in Diffusion Models for Video Super-Resolution (CVPR 2024 · similarity 0.87)
- Arbitrary-Scale Video Super-resolution Guided by Dynamic Context (AAAI 2024 · similarity 0.87)
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.