A small 2M param CNN classifier to predict the quality factor of lossy image codecs. Covers JPEG, JXL, AVIF and WEBP. Dataset (45k) included RAW photography and PNG illustrations.
Overall accuracy was 95.3% on train, 96.6% on val (7% split). Take the predictions with a large grain of salt, its not yet ready for production.
This model will not work properly in the following scenarios:
- Really small images (sub 512px)
- Mutiple resize and/or compression loops (would have ballooned training time for first iteration)
<insert lossy format>renamed to PNG's- Mixed media; low quality JPEG background with an overlaid illustration.
Motivated by research suggesting image models finetuned on many <= q=75 JPEGS had negative outcomes.
Credit: Rimuru original model and original code