Research map / Video / Video segmentation and tracking
Residual Invertible Spatio-Temporal Network for Video Super-Resolution
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 |
|---|---|---|---|
| RISTN vs Liu et al. | video SR · Vid4 4x | PSNR: 25.88 -> 26.13 | Helped |
| add sparse spatio-temporal fusion (ablation) | RISTN-NF · Vid4 4x | PSNR: 25.74 -> 26.13 | Helped |
| use sparse fusion instead of dense fusion (ablation) | RISTN-DF · Vid4 4x | PSNR: 25.97 -> 26.13 | Helped |
| add residual connection to invertible block (ablation) | IB · Set5 4x | PSNR: 31.30 -> 31.65 | Helped |
| add invertible structure to residual block (ablation) | RB · Set5 4x | PSNR: 31.49 -> 31.65 | Helped |
| RIB vs RDN | single-image SR · Set5 4x | PSNR: 32.47 vs 31.65 | Mixed |
| add residual+dense shortcuts to C-LSTM (RDC-LSTM) (ablation) | C-LSTM 10 layers · Vid4 4x | PSNR: 22.13 -> 25.60 | Helped |
| RDC-LSTM instead of RC-LSTM at 3 layers (ablation) | recurrent model · Vid4 4x | PSNR: 25.18 -> 25.16 | Hurt |
| increase layers 3 -> 10 (ablation) | RDC-LSTM · Vid4 4x | PSNR: 25.16 -> 25.60 | Helped |
| increase layers 5 -> 8 (ablation) | C-LSTM · Vid4 4x | PSNR: 24.90 -> 21.98 | Hurt |
Closest papers by meaning
- Fast Spatio-Temporal Residual Network for Video Super-Resolution (CVPR 2019 · similarity 0.93)
- Real-Time Video Super-Resolution With Spatio-Temporal Networks and Motion Compensation (CVPR 2017 · similarity 0.91)
- Building an End-to-End Spatial-Temporal Convolutional Network for Video Super-Resolution (AAAI 2017 · similarity 0.90)
- Recurrent Back-Projection Network for Video Super-Resolution (CVPR 2019 · similarity 0.90)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.86)
- Learning Spatial Adaptation and Temporal Coherence in Diffusion Models for Video Super-Resolution (CVPR 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.