Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/FTVSR

FTVSR

Reported on 44 benchmarks across 11 tasks · 2 papers · 44 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision30 results

3D Human Pose EstimationonREDS4- 4x upscaling
PSNR· 2022-12-27
32.42
best: 33.06 (LRTI-VSR)
SOTA
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
3D Human Pose EstimationonREDS4- 4x upscaling
SSIM· 2022-12-27
0.907
best: 0.9195 (EvTexture+)
SOTA
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
VideoonREDS4- 4x upscaling
PSNR· 2022-12-27
32.42
best: 33.06 (LRTI-VSR)
SOTA
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
VideoonREDS4- 4x upscaling
SSIM· 2022-12-27
0.907
best: 0.9195 (EvTexture+)
SOTA
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
Pose EstimationonREDS4- 4x upscaling
PSNR· 2022-12-27
32.42
best: 33.06 (LRTI-VSR)
SOTA
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
Pose EstimationonREDS4- 4x upscaling
SSIM· 2022-12-27
0.907
best: 0.9195 (EvTexture+)
SOTA
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
Video Super-ResolutiononREDS4- 4x upscaling
PSNR· 2022-12-27
32.42
best: 33.06 (LRTI-VSR)
SOTA
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
Video Super-ResolutiononREDS4- 4x upscaling
SSIM· 2022-12-27
0.907
best: 0.9195 (EvTexture+)
SOTA
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
3D Object Super-ResolutiononREDS4- 4x upscaling
PSNR· 2022-12-27
32.42
best: 33.06 (LRTI-VSR)
SOTA
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
3D Object Super-ResolutiononREDS4- 4x upscaling
SSIM· 2022-12-27
0.907
best: 0.9195 (EvTexture+)
SOTA
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
3D Human Pose EstimationonREDS4- 4x upscaling
PSNR· 2022-08-05
31.82
best: 33.06 (LRTI-VSR)
SOTA
Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution arXiv:2208.03012
3D Human Pose EstimationonREDS4- 4x upscaling
SSIM· 2022-08-05
0.896
best: 0.9195 (EvTexture+)
SOTA
Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution arXiv:2208.03012
VideoonREDS4- 4x upscaling
PSNR· 2022-08-05
31.82
best: 33.06 (LRTI-VSR)
SOTA
Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution arXiv:2208.03012
VideoonREDS4- 4x upscaling
SSIM· 2022-08-05
0.896
best: 0.9195 (EvTexture+)
SOTA
Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution arXiv:2208.03012
Pose EstimationonREDS4- 4x upscaling
PSNR· 2022-08-05
31.82
best: 33.06 (LRTI-VSR)
SOTA
Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution arXiv:2208.03012
Pose EstimationonREDS4- 4x upscaling
SSIM· 2022-08-05
0.896
best: 0.9195 (EvTexture+)
SOTA
Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution arXiv:2208.03012
Video Super-ResolutiononREDS4- 4x upscaling
PSNR· 2022-08-05
31.82
best: 33.06 (LRTI-VSR)
SOTA
Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution arXiv:2208.03012
Video Super-ResolutiononREDS4- 4x upscaling
SSIM· 2022-08-05
0.896
best: 0.9195 (EvTexture+)
SOTA
Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution arXiv:2208.03012
3D Object Super-ResolutiononREDS4- 4x upscaling
PSNR· 2022-08-05
31.82
best: 33.06 (LRTI-VSR)
SOTA
Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution arXiv:2208.03012
3D Object Super-ResolutiononREDS4- 4x upscaling
SSIM· 2022-08-05
0.896
best: 0.9195 (EvTexture+)
SOTA
Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution arXiv:2208.03012
3D Human Pose EstimationonVid4 - 4x upscaling - BD degradation
PSNR· 2022-12-27
28.7
best: 29.54 (RVRT)
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
3D Human Pose EstimationonVid4 - 4x upscaling - BD degradation
SSIM· 2022-12-27
0.869
best: 0.881 (RVRT)
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
VideoonVid4 - 4x upscaling - BD degradation
PSNR· 2022-12-27
28.7
best: 29.54 (RVRT)
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
VideoonVid4 - 4x upscaling - BD degradation
SSIM· 2022-12-27
0.869
best: 0.881 (RVRT)
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
Pose EstimationonVid4 - 4x upscaling - BD degradation
PSNR· 2022-12-27
28.7
best: 29.54 (RVRT)
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
Pose EstimationonVid4 - 4x upscaling - BD degradation
SSIM· 2022-12-27
0.869
best: 0.881 (RVRT)
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
Video Super-ResolutiononVid4 - 4x upscaling - BD degradation
PSNR· 2022-12-27
28.7
best: 29.54 (RVRT)
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
Video Super-ResolutiononVid4 - 4x upscaling - BD degradation
SSIM· 2022-12-27
0.869
best: 0.881 (RVRT)
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
3D Object Super-ResolutiononVid4 - 4x upscaling - BD degradation
PSNR· 2022-12-27
28.7
best: 29.54 (RVRT)
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
3D Object Super-ResolutiononVid4 - 4x upscaling - BD degradation
SSIM· 2022-12-27
0.869
best: 0.881 (RVRT)
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046

Knowledge Base12 results

2D Human Pose EstimationonREDS4- 4x upscaling
PSNR· 2022-12-27
32.42
best: 33.06 (LRTI-VSR)
SOTA
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
2D Human Pose EstimationonREDS4- 4x upscaling
SSIM· 2022-12-27
0.907
best: 0.9195 (EvTexture+)
SOTA
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
3D Absolute Human Pose EstimationonREDS4- 4x upscaling
PSNR· 2022-12-27
32.42
best: 33.06 (LRTI-VSR)
SOTA
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
3D Absolute Human Pose EstimationonREDS4- 4x upscaling
SSIM· 2022-12-27
0.907
best: 0.9195 (EvTexture+)
SOTA
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
2D Human Pose EstimationonREDS4- 4x upscaling
PSNR· 2022-08-05
31.82
best: 33.06 (LRTI-VSR)
SOTA
Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution arXiv:2208.03012
2D Human Pose EstimationonREDS4- 4x upscaling
SSIM· 2022-08-05
0.896
best: 0.9195 (EvTexture+)
SOTA
Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution arXiv:2208.03012
3D Absolute Human Pose EstimationonREDS4- 4x upscaling
PSNR· 2022-08-05
31.82
best: 33.06 (LRTI-VSR)
SOTA
Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution arXiv:2208.03012
3D Absolute Human Pose EstimationonREDS4- 4x upscaling
SSIM· 2022-08-05
0.896
best: 0.9195 (EvTexture+)
SOTA
Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution arXiv:2208.03012
2D Human Pose EstimationonVid4 - 4x upscaling - BD degradation
PSNR· 2022-12-27
28.7
best: 29.54 (RVRT)
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
2D Human Pose EstimationonVid4 - 4x upscaling - BD degradation
SSIM· 2022-12-27
0.869
best: 0.881 (RVRT)
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
3D Absolute Human Pose EstimationonVid4 - 4x upscaling - BD degradation
PSNR· 2022-12-27
28.7
best: 29.54 (RVRT)
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
3D Absolute Human Pose EstimationonVid4 - 4x upscaling - BD degradation
SSIM· 2022-12-27
0.869
best: 0.881 (RVRT)
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046

Graphs6 results

Super-ResolutiononREDS4- 4x upscaling
PSNR· 2022-12-27
32.42
best: 33.06 (LRTI-VSR)
SOTA
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
Super-ResolutiononREDS4- 4x upscaling
SSIM· 2022-12-27
0.907
best: 0.9195 (EvTexture+)
SOTA
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
Super-ResolutiononREDS4- 4x upscaling
PSNR· 2022-08-05
31.82
best: 33.06 (LRTI-VSR)
SOTA
Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution arXiv:2208.03012
Super-ResolutiononREDS4- 4x upscaling
SSIM· 2022-08-05
0.896
best: 0.9195 (EvTexture+)
SOTA
Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution arXiv:2208.03012
Super-ResolutiononVid4 - 4x upscaling - BD degradation
PSNR· 2022-12-27
28.7
best: 29.54 (RVRT)
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
Super-ResolutiononVid4 - 4x upscaling - BD degradation
SSIM· 2022-12-27
0.869
best: 0.881 (RVRT)
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046

Methodology6 results

3DonREDS4- 4x upscaling
PSNR· 2022-12-27
32.42
best: 33.06 (LRTI-VSR)
SOTA
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
3DonREDS4- 4x upscaling
SSIM· 2022-12-27
0.907
best: 0.9195 (EvTexture+)
SOTA
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
3DonREDS4- 4x upscaling
PSNR· 2022-08-05
31.82
best: 33.06 (LRTI-VSR)
SOTA
Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution arXiv:2208.03012
3DonREDS4- 4x upscaling
SSIM· 2022-08-05
0.896
best: 0.9195 (EvTexture+)
SOTA
Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution arXiv:2208.03012
3DonVid4 - 4x upscaling - BD degradation
PSNR· 2022-12-27
28.7
best: 29.54 (RVRT)
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
3DonVid4 - 4x upscaling - BD degradation
SSIM· 2022-12-27
0.869
best: 0.881 (RVRT)
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046

Playing Games6 results

3D Face AnimationonREDS4- 4x upscaling
PSNR· 2022-12-27
32.42
best: 33.06 (LRTI-VSR)
SOTA
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
3D Face AnimationonREDS4- 4x upscaling
SSIM· 2022-12-27
0.907
best: 0.9195 (EvTexture+)
SOTA
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
3D Face AnimationonREDS4- 4x upscaling
PSNR· 2022-08-05
31.82
best: 33.06 (LRTI-VSR)
SOTA
Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution arXiv:2208.03012
3D Face AnimationonREDS4- 4x upscaling
SSIM· 2022-08-05
0.896
best: 0.9195 (EvTexture+)
SOTA
Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution arXiv:2208.03012
3D Face AnimationonVid4 - 4x upscaling - BD degradation
PSNR· 2022-12-27
28.7
best: 29.54 (RVRT)
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
3D Face AnimationonVid4 - 4x upscaling - BD degradation
SSIM· 2022-12-27
0.869
best: 0.881 (RVRT)
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046

Audio6 results

1 Image, 2*2 StitchionREDS4- 4x upscaling
PSNR· 2022-12-27
32.42
best: 33.06 (LRTI-VSR)
SOTA
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
1 Image, 2*2 StitchionREDS4- 4x upscaling
SSIM· 2022-12-27
0.907
best: 0.9195 (EvTexture+)
SOTA
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
1 Image, 2*2 StitchionREDS4- 4x upscaling
PSNR· 2022-08-05
31.82
best: 33.06 (LRTI-VSR)
SOTA
Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution arXiv:2208.03012
1 Image, 2*2 StitchionREDS4- 4x upscaling
SSIM· 2022-08-05
0.896
best: 0.9195 (EvTexture+)
SOTA
Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution arXiv:2208.03012
1 Image, 2*2 StitchionVid4 - 4x upscaling - BD degradation
PSNR· 2022-12-27
28.7
best: 29.54 (RVRT)
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046
1 Image, 2*2 StitchionVid4 - 4x upscaling - BD degradation
SSIM· 2022-12-27
0.869
best: 0.881 (RVRT)
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution arXiv:2212.14046