# Learning Dual Convolutional Neural Networks for Low-Level Vision

arXiv: https://arxiv.org/abs/1805.05020 · HTML: https://mlsanity.com/paper/1805.05020/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 May 2018.

## Built on by (most cited first, 30 of 35)

- [Towards Unified Deep Image Deraining: A Survey and A New Benchmark](https://mlsanity.com/paper/2310.03535/) (2023)
- [Not Just Streaks: Towards Ground Truth for Single Image Deraining](https://mlsanity.com/paper/2206.10779/) (2022)
- [Deep Fourier Up-Sampling](https://mlsanity.com/paper/2210.05171/) (2022)
- [SelfPromer: Self-Prompt Dehazing Transformers with Depth-Consistency](https://mlsanity.com/paper/2303.07033/) (2023)
- [A Wavelet-based Dual-stream Network for Underwater Image Enhancement](https://mlsanity.com/paper/2202.08758/) (2022)
- [Harnessing Scale and Physics: A Multi-Graph Neural Operator Framework for PDEs on Arbitrary Geometries](https://mlsanity.com/paper/2411.15178/) (2024)
- [Mixed Hierarchy Network for Image Restoration](https://mlsanity.com/paper/2302.09554/) (2023)
- [Counting Crowds in Bad Weather](https://mlsanity.com/paper/2306.01209/) (2023)
- [Online-updated High-order Collaborative Networks for Single Image Deraining](https://mlsanity.com/paper/2202.06568/) (2022)
- [RCDNet: An Interpretable Rain Convolutional Dictionary Network for Single Image Deraining](https://mlsanity.com/paper/2107.06808/) (2021)
- [Generalized Real-World Super-Resolution through Adversarial Robustness](https://mlsanity.com/paper/2108.11505/) (2021)
- [One-Step Diffusion Model for Image Motion-Deblurring](https://mlsanity.com/paper/2503.06537/) (2025)
- [Neural Discrimination-Prompted Transformers for Efficient UHD Image Restoration and Enhancement](https://mlsanity.com/paper/2603.00853/) (2026)
- [Learning Detail-Structure Alternative Optimization for Blind Super-Resolution](https://mlsanity.com/paper/2212.01624/) (2022)
- [Dual Residual Attention Network for Image Denoising](https://mlsanity.com/paper/2305.04269/) (2023)
- [Frequency-adaptive Multi-scale Deep Neural Networks](https://mlsanity.com/paper/2410.00053/) (2024)
- [Image Blind Denoising Using Dual Convolutional Neural Network with Skip Connection](https://mlsanity.com/paper/2304.01620/) (2023)
- [Real-Time Video Deblurring via Lightweight Motion Compensation](https://mlsanity.com/paper/2205.12634/) (2022)
- [DCANet: Dual Convolutional Neural Network with Attention for Image Blind Denoising](https://mlsanity.com/paper/2304.01498/) (2023)
- [A Mountain-Shaped Single-Stage Network for Accurate Image Restoration](https://mlsanity.com/paper/2305.05146/) (2023)
- [Decomposition Ascribed Synergistic Learning for Unified Image Restoration](https://mlsanity.com/paper/2308.00759/) (2023)
- [A Unified Foundation Model for All-in-One Multi-Modal Remote Sensing Image Restoration and Fusion with Language Prompting](https://mlsanity.com/paper/2604.05629/) (2026)
- [Multi-target prediction for dummies using two-branch neural networks](https://mlsanity.com/paper/2104.09967/) (2021)
- [Strong and Controllable Blind Image Decomposition](https://mlsanity.com/paper/2403.10520/) (2024)
- [Direction-aware Feature-level Frequency Decomposition for Single Image Deraining](https://mlsanity.com/paper/2106.07941/) (2021)
- [TRNR: Task-Driven Image Rain and Noise Removal with a Few Images Based on Patch Analysis](https://mlsanity.com/paper/2112.01924/) (2021)
- [Exploring Inter-frequency Guidance of Image for Lightweight Gaussian Denoising](https://mlsanity.com/paper/2112.11779/) (2021)
- [How Powerful Potential of Attention on Image Restoration?](https://mlsanity.com/paper/2403.10336/) (2024)
- [Exploring Richer and More Accurate Information via Frequency Selection for Image Restoration](https://mlsanity.com/paper/2407.08950/) (2024)
- [Cross-Resolution Flow Propagation for Foveated Video Super-Resolution](https://mlsanity.com/paper/2212.13525/) (2022)

## Abstract (arXiv)

In this paper, we propose a general dual convolutional neural network (DualCNN) for low-level vision problems, e.g., super-resolution, edge-preserving filtering, deraining and dehazing. These problems usually involve the estimation of two components of the target signals: structures and details. Motivated by this, our proposed DualCNN consists of two parallel branches, which respectively recovers the structures and details in an end-to-end manner. The recovered structures and details can generate the target signals according to the formation model for each particular application. The DualCNN is a flexible framework for low-level vision tasks and can be easily incorporated into existing CNNs. Experimental results show that the DualCNN can be effectively applied to numerous low-level vision tasks with favorable performance against the state-of-the-art methods.