# MDCN: Multi-scale Dense Cross Network for Image Super-Resolution

arXiv: https://arxiv.org/abs/2008.13084 · HTML: https://mlsanity.com/paper/2008.13084/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Aug 2020.

## Built on by (most cited first, 19 of 19)

- [NTIRE 2021 Challenge on Image Deblurring](https://mlsanity.com/paper/2104.14854/) (2021)
- [Feature Distillation Interaction Weighting Network for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2112.08655/) (2021)
- [A Systematic Survey of Deep Learning-based Single-Image Super-Resolution](https://mlsanity.com/paper/2109.14335/) (2021)
- [Cross-receptive Focused Inference Network for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2207.02796/) (2022)
- [Efficient and Accurate Multi-scale Topological Network for Single Image Dehazing](https://mlsanity.com/paper/2102.12135/) (2021)
- [Snow Mask Guided Adaptive Residual Network for Image Snow Removal](https://mlsanity.com/paper/2207.04754/) (2022)
- [Efficient Image Super-Resolution with Feature Interaction Weighted Hybrid Network](https://mlsanity.com/paper/2212.14181/) (2022)
- [A Dive into SAM Prior in Image Restoration](https://mlsanity.com/paper/2305.13620/) (2023)
- [Local Motion and Contrast Priors Driven Deep Network for Infrared Small Target Super-Resolution](https://mlsanity.com/paper/2201.01014/) (2022)
- [Dense Dual-Attention Network for Light Field Image Super-Resolution](https://mlsanity.com/paper/2110.12114/) (2021)
- [Multiple Degradation and Reconstruction Network for Single Image Denoising via Knowledge Distillation](https://mlsanity.com/paper/2204.13873/) (2022)
- [Edge-aware Feature Aggregation Network for Polyp Segmentation](https://mlsanity.com/paper/2309.10523/) (2023)
- [Feedback Pyramid Attention Networks for Single Image Super-Resolution](https://mlsanity.com/paper/2106.06966/) (2021)
- [Toward Real-World Light Field Super-Resolution](https://mlsanity.com/paper/2305.18994/) (2023)
- [Deep Semantic Statistics Matching (D2SM) Denoising Network](https://mlsanity.com/paper/2207.09302/) (2022)
- [A Close Look at Few-shot Real Image Super-resolution from the Distortion Relation Perspective](https://mlsanity.com/paper/2111.13078/) (2021)
- [A Scale-Arbitrary Image Super-Resolution Network Using Frequency-domain Information](https://mlsanity.com/paper/2212.04314/) (2022)
- [MFmamba: A Multi-function Network for Panchromatic Image Resolution Restoration Based on State-Space Model](https://mlsanity.com/paper/2511.18888/) (2025)
- [Efficient Cross-Scale Invertible Hiding Network with Spatial-Frequency Collaboration and Non-Invertible Mechanism](https://mlsanity.com/paper/2606.25547/) (2026)

## Abstract (arXiv)

Convolutional neural networks have been proven to be of great benefit for single-image super-resolution (SISR). However, previous works do not make full use of multi-scale features and ignore the inter-scale correlation between different upsampling factors, resulting in sub-optimal performance. Instead of blindly increasing the depth of the network, we are committed to mining image features and learning the inter-scale correlation between different upsampling factors. To achieve this, we propose a Multi-scale Dense Cross Network (MDCN), which achieves great performance with fewer parameters and less execution time. MDCN consists of multi-scale dense cross blocks (MDCBs), hierarchical feature distillation block (HFDB), and dynamic reconstruction block (DRB). Among them, MDCB aims to detect multi-scale features and maximize the use of image features flow at different scales, HFDB focuses on adaptively recalibrate channel-wise feature responses to achieve feature distillation, and DRB attempts to reconstruct SR images with different upsampling factors in a single model. It is worth noting that all these modules can run independently. It means that these modules can be selectively plugged into any CNN model to improve model performance. Extensive experiments show that MDCN achieves competitive results in SISR, especially in the reconstruction task with multiple upsampling factors. The code will be provided at https://github.com/MIVRC/MDCN-PyTorch.