# Progressive Perception-Oriented Network for Single Image Super-Resolution

arXiv: https://arxiv.org/abs/1907.10399 · HTML: https://mlsanity.com/paper/1907.10399/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jul 2019.

## Built on by (most cited first, 7 of 7)

- [Remote Sensing Image Super-resolution and Object Detection: Benchmark and State of the Art](https://mlsanity.com/paper/2111.03260/) (2021)
- [Enhancing Multi-Scale Implicit Learning in Image Super-Resolution with Integrated Positional Encoding](https://mlsanity.com/paper/2112.05756/) (2021)
- [Flexible Style Image Super-Resolution using Conditional Objective](https://mlsanity.com/paper/2201.04898/) (2022)
- [Image Super-resolution with An Enhanced Group Convolutional Neural Network](https://mlsanity.com/paper/2205.14548/) (2022)
- [Feedback Pyramid Attention Networks for Single Image Super-Resolution](https://mlsanity.com/paper/2106.06966/) (2021)
- [Detail Loss in Super-Resolution Models Based on the Laplacian Pyramid and Repeated Upscaling and Downscaling Process](https://mlsanity.com/paper/2601.09410/) (2026)
- [Super-Resolution of Solar Magnetograms via Adaptive Stratified Ensemble Learning with Uncertainty Estimation](https://mlsanity.com/paper/2609.27131/) (2026)

## Abstract (arXiv)

Recently, it has been demonstrated that deep neural networks can significantly improve the performance of single image super-resolution (SISR). Numerous studies have concentrated on raising the quantitative quality of super-resolved (SR) images. However, these methods that target PSNR maximization usually produce blurred images at large upscaling factor. The introduction of generative adversarial networks (GANs) can mitigate this issue and show impressive results with synthetic high-frequency textures. Nevertheless, these GAN-based approaches always have a tendency to add fake textures and even artifacts to make the SR image of visually higher-resolution. In this paper, we propose a novel perceptual image super-resolution method that progressively generates visually high-quality results by constructing a stage-wise network. Specifically, the first phase concentrates on minimizing pixel-wise error, and the second stage utilizes the features extracted by the previous stage to pursue results with better structural retention. The final stage employs fine structure features distilled by the second phase to produce more realistic results. In this way, we can maintain the pixel, and structural level information in the perceptual image as much as possible. It is useful to note that the proposed method can build three types of images in a feed-forward process. Also, we explore a new generator that adopts multi-scale hierarchical features fusion. Extensive experiments on benchmark datasets show that our approach is superior to the state-of-the-art methods. Code is available at https://github.com/Zheng222/PPON.