🤖 AI Summary
In visual perception, image demosaicing under noise corruption has long suffered from quality degradation and texture distortion, exacerbated by the lack of a unified modeling framework. This paper proposes the first end-to-end joint demosaicing and denoising network. Its core innovation lies in a dual-branch discriminator architecture that synergistically integrates VGG-based perceptual loss and adversarial loss, guiding the generator to perform residual learning and perceptual optimization. The entire model is fully differentiable and requires no multi-stage training. Quantitatively, it achieves significant improvements over contemporary state-of-the-art methods across objective metrics (PSNR, LPIPS) and subjective user studies, while maintaining comparable computational cost. Qualitatively, reconstructed images exhibit more realistic textures and more natural noise suppression. This work establishes a scalable, jointly optimized paradigm for low-level vision tasks.
📝 Abstract
Image demosaicing - one of the most important early stages in digital camera pipelines - addressed the problem of reconstructing a full-resolution image from so-called color-filter-arrays. Despite tremendous progress made in the pase decade, a fundamental issue that remains to be addressed is how to assure the visual quality of reconstructed images especially in the presence of noise corruption. Inspired by recent advances in generative adversarial networks (GAN), we present a novel deep learning approach toward joint demosaicing and denoising (JDD) with perceptual optimization in order to ensure the visual quality of reconstructed images. The key contributions of this work include: 1) we have developed a GAN-based approach toward image demosacing in which a discriminator network with both perceptual and adversarial loss functions are used for quality assurance; 2) we propose to optimize the perceptual quality of reconstructed images by the proposed GAN in an end-to-end manner. Such end-to-end optimization of GAN is particularly effective for jointly exploiting the gain brought by each modular component (e.g., residue learning in the generative network and perceptual loss in the discriminator network). Our extensive experimental results have shown convincingly improved performance over existing state-of-the-art methods in terms of both subjective and objective quality metrics with a comparable computational cost.