# Deep Learning-based Image Super-Resolution Considering Quantitative and Perceptual Quality

arXiv: https://arxiv.org/abs/1809.04789 · HTML: https://mlsanity.com/paper/1809.04789/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Sep 2018.

## Built on by (most cited first, 8 of 8)

- [Perceptual Image Quality Assessment with Transformers](https://mlsanity.com/paper/2104.14730/) (2021)
- [CaDM: Codec-aware Diffusion Modeling for Neural-enhanced Video Streaming](https://mlsanity.com/paper/2211.08428/) (2022)
- [RankSRGAN: Super Resolution Generative Adversarial Networks with Learning to Rank](https://mlsanity.com/paper/2107.09427/) (2021)
- [Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild](https://mlsanity.com/paper/2209.00642/) (2022)
- [Multi-Grid Back-Projection Networks](https://mlsanity.com/paper/2101.00150/) (2021)
- [A General Method to Incorporate Spatial Information into Loss Functions for GAN-based Super-resolution Models](https://mlsanity.com/paper/2403.10589/) (2024)
- [Toward task-driven satellite image super-resolution](https://mlsanity.com/paper/2503.15474/) (2025)
- [Towards Assessing Deep Learning Test Input Generators](https://mlsanity.com/paper/2504.02329/) (2025)

## Abstract (arXiv)

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.