# Analyzing Perception-Distortion Tradeoff using Enhanced Perceptual Super-resolution Network

arXiv: https://arxiv.org/abs/1811.00344 · HTML: https://mlsanity.com/paper/1811.00344/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Nov 2018.

## Built on by (most cited first, 16 of 16)

- [A Comprehensive Review of Deep Learning-based Single Image Super-resolution](https://mlsanity.com/paper/2102.09351/) (2021)
- [Perception-Distortion Balanced ADMM Optimization for Single-Image Super-Resolution](https://mlsanity.com/paper/2208.03324/) (2022)
- [RankSRGAN: Super Resolution Generative Adversarial Networks with Learning to Rank](https://mlsanity.com/paper/2107.09427/) (2021)
- [Perception-Distortion Balanced Super-Resolution: A Multi-Objective Optimization Perspective](https://mlsanity.com/paper/2312.15408/) (2023)
- [Texture-enhanced Light Field Super-resolution with Spatio-Angular Decomposition Kernels](https://mlsanity.com/paper/2111.04069/) (2021)
- [Multi-Grid Back-Projection Networks](https://mlsanity.com/paper/2101.00150/) (2021)
- [Super-Resolution Appearance Transfer for 4D Human Performances](https://mlsanity.com/paper/2108.13739/) (2021)
- [A New Super-Resolution Measurement of Perceptual Quality and Fidelity](https://mlsanity.com/paper/2303.06207/) (2023)
- [Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospects](https://mlsanity.com/paper/2509.22692/) (2025)
- [Mitigating Channel-wise Noise for Single Image Super Resolution](https://mlsanity.com/paper/2112.07589/) (2021)
- [Image Restoration using Feature-guidance](https://mlsanity.com/paper/2201.00187/) (2022)
- [Robust Unpaired Single Image Super-Resolution of Faces](https://mlsanity.com/paper/2201.09109/) (2022)
- [Deep Networks for Image and Video Super-Resolution](https://mlsanity.com/paper/2201.11996/) (2022)
- [Image Superresolution using Scale-Recurrent Dense Network](https://mlsanity.com/paper/2201.11998/) (2022)
- [A General Method to Incorporate Spatial Information into Loss Functions for GAN-based Super-resolution Models](https://mlsanity.com/paper/2403.10589/) (2024)
- [FedVSR: Towards Model-Agnostic Federated Learning in Video Super-Resolution](https://mlsanity.com/paper/2503.13745/) (2025)

## Abstract (arXiv)

Convolutional neural network (CNN) based methods have recently achieved great success for image super-resolution (SR). However, most deep CNN based SR models attempt to improve distortion measures (e.g. PSNR, SSIM, IFC, VIF) while resulting in poor quantified perceptual quality (e.g. human opinion score, no-reference quality measures such as NIQE). Few works have attempted to improve the perceptual quality at the cost of performance reduction in distortion measures. A very recent study has revealed that distortion and perceptual quality are at odds with each other and there is always a trade-off between the two. Often the restoration algorithms that are superior in terms of perceptual quality, are inferior in terms of distortion measures. Our work attempts to analyze the trade-off between distortion and perceptual quality for the problem of single image SR. To this end, we use the well-known SR architecture-enhanced deep super-resolution (EDSR) network and show that it can be adapted to achieve better perceptual quality for a specific range of the distortion measure. While the original network of EDSR was trained to minimize the error defined based on per-pixel accuracy alone, we train our network using a generative adversarial network framework with EDSR as the generator module. Our proposed network, called enhanced perceptual super-resolution network (EPSR), is trained with a combination of mean squared error loss, perceptual loss, and adversarial loss. Our experiments reveal that EPSR achieves the state-of-the-art trade-off between distortion and perceptual quality while the existing methods perform well in either of these measures alone.