Method | Frames REDS/Vimeo | Params(M) | REDS4 PSNR | REDS4 SSIM | Vimeo-90K-T PSNR | Vimeo-90K-T SSIM | Vid4 PSNR | Vid4 SSIM |
---|---|---|---|---|---|---|---|---|
IART 1 | 16/7 | 13.4 | 32.90 | 0.9138 | 38.14 | 0.9528 | 28.26 | 0.8517 |
MFPI 2 | -/- | 7.3 | 32.81 | 0.9106 | 38.28 | 0.9534 | 28.11 | 0.8481 |
PSRT-recurrent 3 | 16/14 | 13.4 | 32.72 | 0.9106 | 38.27 | 0.9536 | 28.07 | 0.8485 |
DFVSR4 | - | 7.1 | 32.76 | 0.9081 | 38.25 | 0.9556 | 27.92 | 0.8427 |
RVRT 5 | 30/14 | 10.8 | 32.75 | 0.9113 | 38.15 | 0.9527 | 27.99 | 0.8426 |
FTVSR++6 | - | 10.8 | 32.42 | 0.907 | - | - | 28.80 | 0.868 |
VRT 7 | 16/7 | 35.6 | 32.19 | 0.9006 | 38.20 | 0.9530 | 27.93 | 0.8425 |
TTVSR 8 | 50/- | 6.8 | 32.12 | 0.9021 | 37.92 | 0.9526 | 28.40 | 0.8643 |
TCNet9 | - | 9.6 | 31.82 | 0.9002 | 37.94 | 0.9514 | 27.48 | 0.8380 |
RTA 10 | 5/7 | 17.0 | 31.30 | 0.8850 | 37.84 | 0.9498 | 27.90 | 0.8380 |
BasicVSR++ 11 | 30/14 | 7.3 | 32.39 | 0.9069 | 37.79 | 0.9500 | 27.79 | 0.8400 |
ETDM 12 | - | 8.4 | 32.15 | 0.9024 | - | - | 28.81 | 0.8725 |
FTVSR13 | - | 10.8 | 31.82 | 0.896 | - | - | 28.31 | 0.860 |
MSHPFNL14 | - | 7.77 | - | - | 36.75 | 0.9406 | 27.70 | 0.8472 |
ICNet15 | - | 18.34 | 31.71 | 0.8963 | 37.72 | 0.9477 | 27.43 | 0.8287 |
IconVSR 16 | 15/14 | 8.7 | 31.67 | 0.8948 | 37.47 | 0.9476 | 27.39 | 0.8279 |
BasicVSR 16 | 15/14 | 6.3 | 31.42 | 0.8909 | 37.18 | 0.9450 | 27.24 | 0.8251 |
VSR-T 17 | 5/7 | 32.6 | 31.19 | 0.8815 | 37.71 | 0.9494 | 27.36 | 0.8258 |
TGA18 | - | 5.8 | - | - | 37.43 | 0.9480 | 27.19 | 0.8213 |
RLSP19 | - | 4.2 | - | - | 37.39 | 0.9470 | 27.15 | 0.8202 |
EDVR20 | 5/7 | 20.6 | 31.09 | 0.8800 | 37.61 | 0.9489 | 27.35 | 0.8264 |
MSFFN21 | - | - | - | - | 37.33 | 0.9467 | 27.23 | 0.8218 |
MuCAN22 | 5/7 | - | 30.88 | 0.8750 | 37.32 | 0.9465 | - | - |
RBPN23 | 7/7 | 12.2 | 30.09 | 0.8590 | 37.07 | 0.9435 | 27.12 | 0.8180 |
PFNL24 | 7/7 | 3.0 | 29.63 | 0.8502 | 36.14 | 0.9363 | 26.73 | 0.8029 |
DUF25 | 7/7 | 5.8 | 28.63 | 0.8251 | - | - | 27.33 | 0.8319 |
FRVSR26 | - | 5.1 | - | - | - | - | 26.69 | 0.8220 |
D3Dnet27 | - | 2.58 | - | - | 35.65 | 0.933 | 26.52 | 0.799 |
TOFlow28 | 5/7 | - | 27.98 | 0.7990 | 33.08 | 0.9054 | 25.89 | 0.7651 |
3DSRnet 29 | - | - | - | - | - | - | 25.71 | 0.7588 |
SPMC30 | - | - | - | - | - | - | 25.52 | 0.76 |
VESPCN31 | - | - | - | - | - | - | 25.35 | 0.7577 |
VSRNet32 | - | 0.27 | - | - | - | - | 22.81 | 0.65 |
Bicubic | - | - | 26.14 | 0.7292 | 31.32 | 0.8684 | 23.78 | 0.6347 |
https://github.com/AIVFI/Video-Frame-Interpolation-Rankings
https://github.com/ChaofWang/Awesome-Super-Resolution
Footnotes
-
An Implicit Alignment for Video Super-Resolution. [arxiv 2023] ↩
-
Multi-Frequency Representation Enhancement with Privilege Information for Video Super-Resolution. [ICCV 2023] ↩
-
Rethinking Alignment in Video Super-Resolution Transformers. [NeurIPS 2022] ↩
-
DFVSR: Directional Frequency Video Super-Resolution via Asymmetric and Enhancement Alignment Network. [IJCAI 2023] ↩
-
Recurrent Video Restoration Transformer with Guided Deformable Attention. [NeurIPS 2022] ↩
-
Learning Degradation-Robust Spatiotemporal Frequency-Transformer for Video Super-Resolution. [TPAMI 2023] ↩
-
VRT: A Video Restoration Transformer. [arxiv 2022] ↩
-
Learning Trajectory-Aware Transformer for Video Super-Resolution. [CVPR 2022] ↩
-
Temporal Consistency Learning of Inter-Frames for Video Super-Resolution. [TCSVT 2023] ↩
-
Revisiting Temporal Alignment for Video Restoration . [CVPR 2022] ↩
-
BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment. [CVPR 2022] ↩
-
Look Back and Forth: Video Super-Resolution with Explicit Temporal Difference Modeling. [CVPR 2022] ↩
-
FTVSR: Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution. [ECCV 2022] ↩
-
A Progressive Fusion Generative Adversarial Network for Realistic and Consistent Video Super-Resolution. [TPAMI 2020] ↩
-
ICNet: Joint Alignment and Reconstruction via Iterative Collaboration for Video Super-Resolution. [ACM MM 2022] ↩
-
BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond. [CVPR 2021] ↩ ↩2
-
Video Super-Resolution Transformer. [arxiv 2021] ↩
-
Video Super-resolution with Temporal Group Attention. [CVPR 2020] ↩
-
Efficient Video Super-Resolution through Recurrent Latent Space Propagation. [ICCVW 2019] ↩
-
EDVR: Video Restoration with Enhanced Deformable Convolutional Networks. [CVPRW 2019] ↩
-
Multi-Stage Feature Fusion Network for Video Super-Resolution. [TIP 2021] ↩
-
MuCAN: Multi-Correspondence Aggregation Network for Video Super-Resolution. [ECCV 2020] ↩
-
Recurrent Back-Projection Network for Video Super-Resolution. [CVPR 2019] ↩
-
Progressive Fusion Video Super-Resolution Network via Exploiting Non-Local Spatio-Temporal Correlations. [ICCV 2019] ↩
-
Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation. [CVPR 2018] ↩
-
Frame-Recurrent Video Super-Resolution. [CVPR 2018] ↩
-
Deformable 3D Convolution for Video Super-Resolution. [SPL 2020] ↩
-
Video Enhancement with Task-Oriented Flow. [IJCV 2019] ↩
-
3DSRnet: Video Super-resolution using 3D Convolutional Neural Networks. [ICIP 2019] ↩
-
Detail-revealing Deep Video Super-resolution. [ICCV 2017] ↩
-
Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation. [CVPR 2017] ↩
-
Video Super-Resolution With Convolutional Neural Networks. [TCI 2016] ↩