[WACV 2024 Oral] - ARNIQA: Learning Distortion Manifold for Image Quality Assessment

Quality-Aware Image-Text Alignment for Opinion-Unaware Image Quality Assessment

Python library for realistically degrading images.

🔷 Effects of Degradations on Deep Neural Network Architectures (official code).

[ICCV 2025] - Image Intrinsic Scale Assessment: Bridging the Gap Between Quality and Resolution

An AI restoration suite for cel animation, featuring specialized Real-ESRGAN models and the physics-based degradation simulator used to train them.

Can we perform face hallucination using limited set of unaligned pairs?

Realistic synthetic degradation of document images — simulate scans, phone photos, photocopies, and aged paper for data augmentation in document AI / OCR / layout analysis pipelines. 23 physically-motivated transforms, 6 presets, CLI + Python API.

Robust CNN & CapsuleNet benchmarks for noisy images – modern TensorFlow 2/Keras 3 support.

🎨 Enhance cel animation with specialized AI models and a physics-based simulator for effective restoration of historical animation defects.