Research map / Video / Video segmentation and tracking
Learning Trajectory-Aware Transformer 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 |
|---|---|---|---|
| use trajectory-aware Transformer instead of IconVSR | Video super-resolution · REDS4 | PSNR: 31.67 -> 32.12 | Helped |
| use trajectory-aware Transformer instead of IconVSR | Video super-resolution · Vid4 | PSNR: 28.04 -> 28.40 | Helped |
| use trajectory-aware Transformer instead of IconVSR | Video super-resolution · UDM10 | PSNR: 40.03 -> 40.41 | Helped |
| use trajectory-aware Transformer instead of IconVSR | Video super-resolution · Vimeo-90K-T | PSNR: 37.84 -> 37.92 | Helped |
| add trajectory generation to the Base model (ablation) | TTVSR · REDS4 | PSNR: 30.46 -> 31.91 | Helped |
| add trajectory-aware attention to trajectory generation (ablation) | TTVSR · REDS4 | PSNR: 31.91 -> 31.99 | Helped |
| increase sampled frames from 5 to 45 (ablation) | Trajectory-aware attention · REDS4 | PSNR: 31.89 -> 32.01 | Helped |
| add cross-scale feature tokenization with token sizes 4, 6 (ablation) | Base+TG+TA · REDS4 | PSNR: 31.99 -> 32.08 | Helped |
| add cross-scale feature tokenization with token sizes 4, 6, 8 (ablation) | Base+TG+TA · REDS4 | PSNR: 31.99 -> 32.12 | Helped |
| replace token sizes 4, 6, 8 with 6, 9, 12 (ablation) | TTVSR · REDS4 | PSNR: 32.12 -> 31.95 | Hurt |
| replace token sizes 4, 6, 8 with 8, 12, 16 (ablation) | TTVSR · REDS4 | PSNR: 32.12 -> 31.91 | Hurt |
Closest papers by meaning
- EvEnhancer: Empowering Effectiveness, Efficiency and Generalizability for Continuous Space-Time Video Super-Resolution with Events (CVPR 2025 · similarity 0.88)
- BF-STVSR: B-Splines and Fourier---Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution (CVPR 2025 · similarity 0.88)
- Self-supervised ControlNet with Spatio-Temporal Mamba for Real-world Video Super-resolution (CVPR 2025 · similarity 0.88)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.87)
- Sequence Matters: Harnessing Video Models in 3D Super-Resolution (AAAI 2025 · similarity 0.87)
- Learning Spatial Adaptation and Temporal Coherence in Diffusion Models for Video Super-Resolution (CVPR 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.