thera-rdn-air

Overview

This is a model from the paper Thera: Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields. It enables SOTA arbitrary-scale super-resolution, leveraging a built-in analytically correct observation model for anti-aliasing when moving across scales.

Project page: https://therasr.github.io Code: https://github.com/prs-eth/thera

Model Details

• Description: This model can be used to enable super-resolution of single images at arbitrary, non-integer scaling factors.
• Backbone: RDN
• Variant: Air
• Training Dataset: DIV2K

Sample Usage

Super-resolve any image with:

> ./super_resolve.py IN_FILE OUT_FILE --scale 3.14 --checkpoint thera-rdn-pro.pkl

License

Apache-2.0