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/EDT-B

EDT-B

Reported on 16 benchmarks across 4 tasks · 1 paper · 16 SOTA

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

Computer Vision8 results

Image Super-ResolutiononSet5 - 3x upscaling
PSNR· uses extra data· 2021-12-19
35.13
best: 35.35 (HMA†)
SOTA
On Efficient Transformer-Based Image Pre-training for Low-Level Vision arXiv:2112.10175
Image Super-ResolutiononSet5 - 3x upscaling
SSIM· uses extra data· 2021-12-19
0.9328
best: 0.938 (Hi-IR-L)
SOTA
On Efficient Transformer-Based Image Pre-training for Low-Level Vision arXiv:2112.10175
Image Super-ResolutiononSet5 - 2x upscaling
PSNR· uses extra data· 2021-12-19
38.63
best: 39.14 (DRCT-L)
SOTA
On Efficient Transformer-Based Image Pre-training for Low-Level Vision arXiv:2112.10175
Image Super-ResolutiononSet5 - 2x upscaling
SSIM· uses extra data· 2021-12-19
0.9632
best: 0.9663 (Hi-IR-L)
SOTA
On Efficient Transformer-Based Image Pre-training for Low-Level Vision arXiv:2112.10175
3D Object Super-ResolutiononSet5 - 3x upscaling
PSNR· uses extra data· 2021-12-19
35.13
best: 35.35 (HMA†)
SOTA
On Efficient Transformer-Based Image Pre-training for Low-Level Vision arXiv:2112.10175
3D Object Super-ResolutiononSet5 - 3x upscaling
SSIM· uses extra data· 2021-12-19
0.9328
best: 0.938 (Hi-IR-L)
SOTA
On Efficient Transformer-Based Image Pre-training for Low-Level Vision arXiv:2112.10175
3D Object Super-ResolutiononSet5 - 2x upscaling
PSNR· uses extra data· 2021-12-19
38.63
best: 39.14 (DRCT-L)
SOTA
On Efficient Transformer-Based Image Pre-training for Low-Level Vision arXiv:2112.10175
3D Object Super-ResolutiononSet5 - 2x upscaling
SSIM· uses extra data· 2021-12-19
0.9632
best: 0.9663 (Hi-IR-L)
SOTA
On Efficient Transformer-Based Image Pre-training for Low-Level Vision arXiv:2112.10175

Graphs4 results

Super-ResolutiononSet5 - 3x upscaling
PSNR· uses extra data· 2021-12-19
35.13
best: 35.35 (HMA†)
SOTA
On Efficient Transformer-Based Image Pre-training for Low-Level Vision arXiv:2112.10175
Super-ResolutiononSet5 - 3x upscaling
SSIM· uses extra data· 2021-12-19
0.9328
best: 0.938 (Hi-IR-L)
SOTA
On Efficient Transformer-Based Image Pre-training for Low-Level Vision arXiv:2112.10175
Super-ResolutiononSet5 - 2x upscaling
PSNR· uses extra data· 2021-12-19
38.63
best: 39.14 (DRCT-L)
SOTA
On Efficient Transformer-Based Image Pre-training for Low-Level Vision arXiv:2112.10175
Super-ResolutiononSet5 - 2x upscaling
SSIM· uses extra data· 2021-12-19
0.9632
best: 0.9663 (Hi-IR-L)
SOTA
On Efficient Transformer-Based Image Pre-training for Low-Level Vision arXiv:2112.10175

Methodology4 results

16konSet5 - 3x upscaling
PSNR· uses extra data· 2021-12-19
35.13
best: 35.35 (HMA†)
SOTA
On Efficient Transformer-Based Image Pre-training for Low-Level Vision arXiv:2112.10175
16konSet5 - 3x upscaling
SSIM· uses extra data· 2021-12-19
0.9328
best: 0.938 (Hi-IR-L)
SOTA
On Efficient Transformer-Based Image Pre-training for Low-Level Vision arXiv:2112.10175
16konSet5 - 2x upscaling
PSNR· uses extra data· 2021-12-19
38.63
best: 39.14 (DRCT-L)
SOTA
On Efficient Transformer-Based Image Pre-training for Low-Level Vision arXiv:2112.10175
16konSet5 - 2x upscaling
SSIM· uses extra data· 2021-12-19
0.9632
best: 0.9663 (Hi-IR-L)
SOTA
On Efficient Transformer-Based Image Pre-training for Low-Level Vision arXiv:2112.10175