# Efficient Deep Neural Network for Photo-realistic Image Super-Resolution

arXiv: https://arxiv.org/abs/1903.02240 · HTML: https://mlsanity.com/paper/1903.02240/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Mar 2019.

## Built on by (most cited first, 5 of 5)

- [N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution](https://mlsanity.com/paper/2211.11436/) (2022)
- [Multi-scale Attention Guided Pose Transfer](https://mlsanity.com/paper/2202.06777/) (2022)
- [Joint Super-Resolution and Inverse Tone-Mapping: A Feature Decomposition Aggregation Network and A New Benchmark](https://mlsanity.com/paper/2207.03367/) (2022)
- [Super-Resolution Appearance Transfer for 4D Human Performances](https://mlsanity.com/paper/2108.13739/) (2021)
- [MSIQ: Moment-based Scale-Invariant Quality Measure for Single Image Super-Resolution](https://mlsanity.com/paper/2605.17588/) (2026)

## Abstract (arXiv)

Recent progress in deep learning-based models has improved photo-realistic (or perceptual) single-image super-resolution significantly. However, despite their powerful performance, many methods are difficult to apply to real-world applications because of the heavy computational requirements. To facilitate the use of a deep model under such demands, we focus on keeping the network efficient while maintaining its performance. In detail, we design an architecture that implements a cascading mechanism on a residual network to boost the performance with limited resources via multi-level feature fusion. In addition, our proposed model adopts group convolution and recursive schemes in order to achieve extreme efficiency. We further improve the perceptual quality of the output by employing the adversarial learning paradigm and a multi-scale discriminator approach. The performance of our method is investigated through extensive internal experiments and benchmarks using various datasets. Our results show that our models outperform the recent methods with similar complexity, for both traditional pixel-based and perception-based tasks.