Research map / Video / Video segmentation and tracking
TDAN: Temporally-Deformable Alignment Network 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 TDAN feature-level temporal alignment instead of the strongest listed SISR/VSR baseline | Video super-resolution · Vid4, BI | PSNR (dB): 25.52 -> 26.24 | Helped |
| Use TDAN feature-level temporal alignment instead of the strongest listed SISR/VSR baseline | Video super-resolution · Vid4, BI | SSIM: 0.748 -> 0.780 | Helped |
| Use TDAN instead of DUF | Video super-resolution · Vid4, BD | PSNR (dB): 26.21 -> 26.58 | Helped |
| Use TDAN instead of DUF | Video super-resolution · Vid4, BD | SSIM: 0.814 -> 0.801 | Hurt |
| Add supporting frames without temporal alignment (ablation) | SISR model · Vimeo Super-Resolution validation | PSNR | Helped |
| Add temporal alignment to the multi-frame model (ablation) | MFSR · Vimeo Super-Resolution validation | PSNR | Helped |
| Increase deformable convolutional layers from 2 to 5 (ablation) | TDAN · Vimeo Super-Resolution validation | PSNR | Helped |
| Remove aligned-frame reconstruction and the alignment loss (ablation) | TDAN · Vimeo Super-Resolution validation | PSNR | Hurt |
Closest papers by meaning
- Rethinking Alignment in Video Super-Resolution Transformers (NeurIPS 2022 · similarity 0.90)
- Sequence Matters: Harnessing Video Models in 3D Super-Resolution (AAAI 2025 · similarity 0.87)
- Enhancing Video Super-Resolution via Implicit Resampling-based Alignment (CVPR 2024 · similarity 0.86)
- VideoGigaGAN: Towards Detail-rich Video Super-Resolution (CVPR 2025 · similarity 0.86)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.86)
- Semantic Lens: Instance-Centric Semantic Alignment for Video Super-resolution (AAAI 2024 · 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.