sr-implicit-downsampled-fast

2y7c3 / Super-Resolution-Neural-Operator

Super-Resolution Neural Operator, in CVPR 2023

MIT License

137 stars 12 forks source link

sr-implicit-downsampled-fast #6

Open Jinchen2028 opened 1 year ago

Jinchen2028 commented 1 year ago

Thank you very much for sharing this excellent work, in which we noticed the use of "sr-implicit-downsampled-fast" in this work, and I would like to know what changes were made to make this "quick method" faster compared to "sr-implicit-downsampled" in LIIF?

2y7c3 commented 1 year ago

We follow a prior implementation and utilize 1×1 convolutions to replace all the linear layers in SRNO, since they have a GPU-friendly data structure.