Paper: "A-ESRGAN: Training Real-World Blind Super-Resolution with Attention U-Net Discriminators", Wei et al 2021. "Main idea: Introduce attention U-net into the field of blind real world image super resolution. We aims to provide a super resolution method with sharper result and less distortion."

• A-ESRGAN

  1 106 0.0 Python

  [PRICAI 2023] A-ESRGAN aims to provide better super-resolution images by using multi-scale attention U-net discriminators.

  

I went to have a look at the code backing this because I've been following the development of SRGAN architecture closely. Link to the repo: A-ESRGAN. I was more than disappointed, it actually made me angry.

• Real-ESRGAN

  131 26,111 2.7 Python

  Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

It all looks well and good, neatly arranged, until you dive a bit into the code and layout, and you come to realize that this entire repo is a (in most cases literally) copy/paste of Xinntao's Real-ESRGAN work with miniscule rearrangements and induced mistakes. About what I'd expect from students trying to get away with being lazy on an assignment.

• InfluxDB

  www.influxdata.com sponsored

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

• ESRGAN

  21 5,707 0.0 Python

  ECCV18 Workshops - Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution. The training codes are in BasicSR.

There are two Generator architectures that are in the code, however these are actually just sitting there unused, likely from work that did not pan out because if you look at their inference code it's not used at all. Instead they directly import the plain old vanilla RRDB architecture from BasicSR yet again another Xinntao repository. Seeing the theme here.

Suggest a related project