Deep Learning-based Image Super-Resolution Considering Quantitative and Perceptual Quality
This addresses the challenge of balancing image fidelity and naturalness in super-resolution for applications like image enhancement, though it appears incremental.
The paper tackles the tradeoff between quantitative and perceptual quality in image super-resolution by proposing a deep learning method that improves perceptual quality while maintaining quantitative performance, showing more satisfactory results than existing methods.
Recently, it has been shown that in super-resolution, there exists a tradeoff relationship between the quantitative and perceptual quality of super-resolved images, which correspond to the similarity to the ground-truth images and the naturalness, respectively. In this paper, we propose a novel super-resolution method that can improve the perceptual quality of the upscaled images while preserving the conventional quantitative performance. The proposed method employs a deep network for multi-pass upscaling in company with a discriminator network and two quantitative score predictor networks. Experimental results demonstrate that the proposed method achieves a good balance of the quantitative and perceptual quality, showing more satisfactory results than existing methods.