PyNET-QxQ: An Efficient PyNET Variant for QxQ Bayer Pattern Demosaicing in CMOS Image Sensors

Abstract

Deep learning-based image signal processor (ISP) models for mobile cameras can generate high-quality images that rival those of professional DSLR cameras. However, their computational demands often make them unsuitable for mobile settings. Additionally, modern mobile cameras employ non-Bayer color filter arrays (CFA) such as Quad Bayer, Nona Bayer, and QxQ Bayer to enhance image quality, yet most existing deep learning-based ISP (or demosaicing) models focus primarily on standard Bayer CFAs. In this study, we present PyNET-QxQ, a lightweight demosaicing model specifically designed for QxQ Bayer CFA patterns, which is derived from the original PyNET. We also propose a knowledge distillation method called progressive distillation to train the reduced network more effectively. Consequently, PyNET-QxQ contains less than 2.5% of the parameters of the original PyNET while preserving its performance. Experiments using QxQ images captured by a proto type QxQ camera sensor show that PyNET-QxQ outperforms existing conventional algorithms in terms of texture and edge reconstruction, despite its significantly reduced parameter count.

Accepted by IEEE Access

References in corpus (9)

• Distilling the Knowledge in a Neural Network
• FitNets: Hints for Thin Deep Nets
• Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
• Adaptive Multi-Teacher Multi-level Knowledge Distillation
• Compressing GANs using Knowledge Distillation
• PyNET-CA: Enhanced PyNET with Channel Attention for End-to-End Mobile Image Signal Processing
• SAGAN: Adversarial Spatial-asymmetric Attention for Noisy Nona-Bayer Reconstruction
• Local-Selective Feature Distillation for Single Image Super-Resolution
• Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher