# Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Network

arXiv: https://arxiv.org/abs/1707.05425 · HTML: https://mlsanity.com/paper/1707.05425/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jul 2017.

## Built on by (most cited first, 17 of 17)

- [Quality Assessment of Image Super-Resolution: Balancing Deterministic and Statistical Fidelity](https://mlsanity.com/paper/2207.08689/) (2022)
- [Continuous Remote Sensing Image Super-Resolution based on Context Interaction in Implicit Function Space](https://mlsanity.com/paper/2302.08046/) (2023)
- [Image Super-Resolution Quality Assessment: Structural Fidelity Versus Statistical Naturalness](https://mlsanity.com/paper/2105.07139/) (2021)
- [Point-Cloud Deep Learning of Porous Media for Permeability Prediction](https://mlsanity.com/paper/2107.14038/) (2021)
- [Hyperspectral Demosaicing of Snapshot Camera Images Using Deep Learning](https://mlsanity.com/paper/2211.15435/) (2022)
- [Selfie Periocular Verification using an Efficient Super-Resolution Approach](https://mlsanity.com/paper/2102.08449/) (2021)
- [Identity-Preserving Pose-Robust Face Hallucination Through Face Subspace Prior](https://mlsanity.com/paper/2111.10634/) (2021)
- [SDT-DCSCN for Simultaneous Super-Resolution and Deblurring of Text Images](https://mlsanity.com/paper/2201.05865/) (2022)
- [QMRNet: Quality Metric Regression for EO Image Quality Assessment and Super-Resolution](https://mlsanity.com/paper/2210.06618/) (2022)
- [Effects of Data Enrichment with Image Transformations on the Performance of Deep Networks](https://mlsanity.com/paper/2306.07724/) (2023)
- [Fully Convolutional Fractional Scaling](https://mlsanity.com/paper/2203.10670/) (2022)
- [High-Resolution Bathymetric Reconstruction From Sidescan Sonar With Deep Neural Networks](https://mlsanity.com/paper/2206.07810/) (2022)
- [Super-Resolution and Image Re-projection for Iris Recognition](https://mlsanity.com/paper/2210.11129/) (2022)
- [Real-World Video for Zoom Enhancement based on Spatio-Temporal Coupling](https://mlsanity.com/paper/2306.13875/) (2023)
- [Efficient and Accurate Hyperspectral Image Demosaicing with Neural Network Architectures](https://mlsanity.com/paper/2403.12050/) (2023)
- [Unmasking unlearnable models: a classification challenge for biomedical images without visible cues](https://mlsanity.com/paper/2407.19773/) (2024)
- [Generative Model-Assisted Demosaicing for Cross-multispectral Cameras](https://mlsanity.com/paper/2503.02322/) (2025)

## Abstract (arXiv)

We propose a highly efficient and faster Single Image Super-Resolution (SISR) model with Deep Convolutional neural networks (Deep CNN). Deep CNN have recently shown that they have a significant reconstruction performance on single-image super-resolution. Current trend is using deeper CNN layers to improve performance. However, deep models demand larger computation resources and is not suitable for network edge devices like mobile, tablet and IoT devices. Our model achieves state of the art reconstruction performance with at least 10 times lower calculation cost by Deep CNN with Residual Net, Skip Connection and Network in Network (DCSCN). A combination of Deep CNNs and Skip connection layers is used as a feature extractor for image features on both local and global area. Parallelized 1x1 CNNs, like the one called Network in Network, is also used for image reconstruction. That structure reduces the dimensions of the previous layer's output for faster computation with less information loss, and make it possible to process original images directly. Also we optimize the number of layers and filters of each CNN to significantly reduce the calculation cost. Thus, the proposed algorithm not only achieves the state of the art performance but also achieves faster and efficient computation. Code is available at https://github.com/jiny2001/dcscn-super-resolution