Implementation of UniRestorer++: Scalable Universal Image Restoration with Multi-Granularity Degradation Modeling
-
Updated
Oct 26, 2026 - Python
Implementation of UniRestorer++: Scalable Universal Image Restoration with Multi-Granularity Degradation Modeling
Companion repo for A 2×2 Controlled Ablation of Data Quality and Capacity in Transformer MT. Contains the QE-filtered fine-tuning pipeline (Section 7), CometKiwi-22 scoring/filtering scripts, and the full paper LaTeX source. Pretraining lives in Machine_translation
A tool for scaling machine learning models
To associate your repository with the model-scaling topic, visit your repo's landing page and select "manage topics."