# DDet: Dual-path Dynamic Enhancement Network for Real-World Image Super-Resolution

arXiv: https://arxiv.org/abs/2002.11079 · HTML: https://mlsanity.com/paper/2002.11079/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Feb 2020.

## Built on by (most cited first, 13 of 13)

- [IDF-CR: Iterative Diffusion Process for Divide-and-Conquer Cloud Removal in Remote-sensing Images](https://mlsanity.com/paper/2403.11870/) (2024)
- [Real-World Image Super-Resolution by Exclusionary Dual-Learning](https://mlsanity.com/paper/2206.02609/) (2022)
- [Learning from Multi-Perception Features for Real-Word Image Super-resolution](https://mlsanity.com/paper/2305.18547/) (2023)
- [Criteria Comparative Learning for Real-scene Image Super-Resolution](https://mlsanity.com/paper/2207.12767/) (2022)
- [PFT-SSR: Parallax Fusion Transformer for Stereo Image Super-Resolution](https://mlsanity.com/paper/2303.13807/) (2023)
- [NegVSR: Augmenting Negatives for Generalized Noise Modeling in Real-World Video Super-Resolution](https://mlsanity.com/paper/2305.14669/) (2023)
- [GTAE: Graph-Transformer based Auto-Encoders for Linguistic-Constrained Text Style Transfer](https://mlsanity.com/paper/2102.00769/) (2021)
- [Learning Dual-Level Deformable Implicit Representation for Real-World Scale Arbitrary Super-Resolution](https://mlsanity.com/paper/2403.10925/) (2024)
- [A Feature Reuse Framework with Texture-adaptive Aggregation for Reference-based Super-Resolution](https://mlsanity.com/paper/2306.01500/) (2023)
- [Image super-resolution via dynamic network](https://mlsanity.com/paper/2310.10413/) (2023)
- [Adaptive Blind Super-Resolution Network for Spatial-Specific and Spatial-Agnostic Degradations](https://mlsanity.com/paper/2506.07705/) (2025)
- [SRTGAN: Triplet Loss based Generative Adversarial Network for Real-World Super-Resolution](https://mlsanity.com/paper/2211.12180/) (2022)
- [PDE: Gene Effect Inspired Parameter Dynamic Evolution for Low-light Image Enhancement](https://mlsanity.com/paper/2505.09196/) (2025)

## Abstract (arXiv)

Different from traditional image super-resolution task, real image super-resolution(Real-SR) focus on the relationship between real-world high-resolution(HR) and low-resolution(LR) image. Most of the traditional image SR obtains the LR sample by applying a fixed down-sampling operator. Real-SR obtains the LR and HR image pair by incorporating different quality optical sensors. Generally, Real-SR has more challenges as well as broader application scenarios. Previous image SR methods fail to exhibit similar performance on Real-SR as the image data is not aligned inherently. In this article, we propose a Dual-path Dynamic Enhancement Network(DDet) for Real-SR, which addresses the cross-camera image mapping by realizing a dual-way dynamic sub-pixel weighted aggregation and refinement. Unlike conventional methods which stack up massive convolutional blocks for feature representation, we introduce a content-aware framework to study non-inherently aligned image pair in image SR issue. First, we use a content-adaptive component to exhibit the Multi-scale Dynamic Attention(MDA). Second, we incorporate a long-term skip connection with a Coupled Detail Manipulation(CDM) to perform collaborative compensation and manipulation. The above dual-path model is joint into a unified model and works collaboratively. Extensive experiments on the challenging benchmarks demonstrate the superiority of our model.