An Extensible and Lightweight Unified Architecture for Demosaicing Pixel-bin Image Sensors
This work addresses the need for efficient, multi-CFA demosaicing in smartphone cameras, reducing onboard resource usage and development effort.
The paper proposes a modular unified architecture for demosaicing pixel-bin image sensors that achieves higher image quality while being lightweight and extensible across different CFA types, and introduces a learning-free CFA-identification module for plug-and-play operation.
Pixel-bin image sensors are becoming the default choice for smartphone cameras due to their resolution vs light-gathering trade-off. However, their larger inter-color separation compared to the Bayer color filter array (CFA) makes them challenging to demosaic. Furthermore, existing deep learning-based demosaicing methods are CFA-specific, requiring multiple individual models that take up precious onboard resources and demand larger development and maintenance efforts. In this work, we propose a modular unified architecture for demosaicing various pixel-bin sensors that provides higher image quality while being extensible and lightweight. Additionally, to enable plug-and-play operation, we introduce a learning-free CFA-identification module to detect the CFA type of raw data accurately.