# HQG-Net: Unpaired Medical Image Enhancement with High-Quality Guidance

arXiv: https://arxiv.org/abs/2307.07829 · HTML: https://mlsanity.com/paper/2307.07829/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 61 references that are in the map.
- First posted on arXiv 15 Jul 2023.

## Builds on (most cited first, 26 of 26)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (2017)
- [Learning Texture Transformer Network for Image Super-Resolution](https://mlsanity.com/paper/2006.04139/) (2020)
- [Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection](https://mlsanity.com/paper/2203.16220/) (2022)
- [A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images](https://mlsanity.com/paper/1612.00799/) (2016)
- [Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks](https://mlsanity.com/paper/1604.04382/) (2016)
- [Photorealistic Style Transfer via Wavelet Transforms](https://mlsanity.com/paper/1903.09760/) (2019)
- [StyleSwin: Transformer-based GAN for High-resolution Image Generation](https://mlsanity.com/paper/2112.10762/) (2021)
- [Image Super-Resolution by Neural Texture Transfer](https://mlsanity.com/paper/1903.00834/) (2019)
- [Dual Adversarial Network: Toward Real-world Noise Removal and Noise Generation](https://mlsanity.com/paper/2007.05946/) (2020)
- [Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Grouping](https://mlsanity.com/paper/2305.11003/) (2023)
- [CrossNet: An End-to-end Reference-based Super Resolution Network using Cross-scale Warping](https://mlsanity.com/paper/1807.10547/) (2018)
- [MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution](https://mlsanity.com/paper/2106.02299/) (2021)
- [Progressively Normalized Self-Attention Network for Video Polyp Segmentation](https://mlsanity.com/paper/2105.08468/) (2021)
- [Robust Reference-based Super-Resolution via C2-Matching](https://mlsanity.com/paper/2106.01863/) (2021)
- [Evaluation of Retinal Image Quality Assessment Networks in Different Color-spaces](https://mlsanity.com/paper/1907.05345/) (2019)
- [Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification](https://mlsanity.com/paper/2204.04567/) (2022)
- [ADN: Artifact Disentanglement Network for Unsupervised Metal Artifact Reduction](https://mlsanity.com/paper/1908.01104/) (2019)
- [A Novel Geometric Framework on Gram Matrix Trajectories for Human Behavior Understanding](https://mlsanity.com/paper/1807.00676/) (2018)
- [Study Group Learning: Improving Retinal Vessel Segmentation Trained with Noisy Labels](https://mlsanity.com/paper/2103.03451/) (2021)
- [Task-Oriented Convex Bilevel Optimization with Latent Feasibility](https://mlsanity.com/paper/1907.03083/) (2019)

## Built on by (most cited first, 30 of 36)

- [Taming Rectified Flow for Inversion and Editing](https://mlsanity.com/paper/2411.04746/) (2024)
- [Diffusion Models in Low-Level Vision: A Survey](https://mlsanity.com/paper/2406.11138/) (2024)
- [Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model](https://mlsanity.com/paper/2311.11638/) (2023)
- [Consistent123: One Image to Highly Consistent 3D Asset Using Case-Aware Diffusion Priors](https://mlsanity.com/paper/2309.17261/) (2023)
- [Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objects](https://mlsanity.com/paper/2308.03166/) (2023)
- [Rank-DETR for High Quality Object Detection](https://mlsanity.com/paper/2310.08854/) (2023)
- [MultiBooth: Towards Generating All Your Concepts in an Image from Text](https://mlsanity.com/paper/2404.14239/) (2024)
- [MambaDFuse: A Mamba-based Dual-phase Model for Multi-modality Image Fusion](https://mlsanity.com/paper/2404.08406/) (2024)
- [JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration](https://mlsanity.com/paper/2504.04158/) (2025)
- [Towards Universal Modal Tracking with Online Dense Temporal Token Learning](https://mlsanity.com/paper/2507.20177/) (2025)
- [RUN: Reversible Unfolding Network for Concealed Object Segmentation](https://mlsanity.com/paper/2501.18783/) (2025)
- [Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network](https://mlsanity.com/paper/2406.07966/) (2024)
- [UnfoldIR: Rethinking Deep Unfolding Network in Illumination Degradation Image Restoration](https://mlsanity.com/paper/2505.06683/) (2025)
- [Consistency Regularization for Generalizable Source-free Domain Adaptation](https://mlsanity.com/paper/2308.01587/) (2023)
- [RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditions](https://mlsanity.com/paper/2508.03077/) (2025)
- [Reversible Unfolding Network for Concealed Visual Perception with Generative Refinement](https://mlsanity.com/paper/2508.15027/) (2025)
- [Concealed Object Segmentation with Hierarchical Coherence Modeling](https://mlsanity.com/paper/2401.11767/) (2024)
- [Nested Unfolding Network for Real-World Concealed Object Segmentation](https://mlsanity.com/paper/2511.18164/) (2025)
- [SCALER: SAM-Enhanced Collaborative Learning for Label-Deficient Concealed Object Segmentation](https://mlsanity.com/paper/2511.18136/) (2025)
- [Revisiting the Generalization Problem of Low-level Vision Models Through the Lens of Image Deraining](https://mlsanity.com/paper/2502.12600/) (2025)
- [Segment Concealed Objects with Incomplete Supervision](https://mlsanity.com/paper/2506.08955/) (2025)
- [Enhancing Zero-Shot Brain Tumor Subtype Classification via Fine-Grained Patch-Text Alignment](https://mlsanity.com/paper/2508.01602/) (2025)
- [IQPFR: An Image Quality Prior for Blind Face Restoration and Beyond](https://mlsanity.com/paper/2503.09294/) (2025)
- [Beyond Ground-Truth: Leveraging Image Quality Priors for Real-World Image Restoration](https://mlsanity.com/paper/2603.29773/) (2026)
- [An Anisotropic Cross-View Texture Transfer with Multi-Reference Non-Local Attention for CT Slice Interpolation](https://mlsanity.com/paper/2509.20242/) (2025)
- [GAN-HA: A generative adversarial network with a novel heterogeneous dual-discriminator network and a new attention-based fusion strategy for infrared and visible image fusion](https://mlsanity.com/paper/2404.15992/) (2024)
- [Multi-Scale Target-Aware Representation Learning for Fundus Image Enhancement](https://mlsanity.com/paper/2505.01831/) (2025)
- [Fast Kernel-Space Diffusion for Remote Sensing Pansharpening](https://mlsanity.com/paper/2505.18991/) (2025)
- [FADE: Adversarial Concept Erasure in Flow Models](https://mlsanity.com/paper/2507.12283/) (2025)
- [Robust Concept Erasure in Diffusion Models: A Theoretical Perspective on Security and Robustness](https://mlsanity.com/paper/2509.12024/) (2025)

## Abstract (arXiv)

Unpaired Medical Image Enhancement (UMIE) aims to transform a low-quality (LQ) medical image into a high-quality (HQ) one without relying on paired images for training. While most existing approaches are based on Pix2Pix/CycleGAN and are effective to some extent, they fail to explicitly use HQ information to guide the enhancement process, which can lead to undesired artifacts and structural distortions. In this paper, we propose a novel UMIE approach that avoids the above limitation of existing methods by directly encoding HQ cues into the LQ enhancement process in a variational fashion and thus model the UMIE task under the joint distribution between the LQ and HQ domains. Specifically, we extract features from an HQ image and explicitly insert the features, which are expected to encode HQ cues, into the enhancement network to guide the LQ enhancement with the variational normalization module. We train the enhancement network adversarially with a discriminator to ensure the generated HQ image falls into the HQ domain. We further propose a content-aware loss to guide the enhancement process with wavelet-based pixel-level and multi-encoder-based feature-level constraints. Additionally, as a key motivation for performing image enhancement is to make the enhanced images serve better for downstream tasks, we propose a bi-level learning scheme to optimize the UMIE task and downstream tasks cooperatively, helping generate HQ images both visually appealing and favorable for downstream tasks. Experiments on three medical datasets, including two newly collected datasets, verify that the proposed method outperforms existing techniques in terms of both enhancement quality and downstream task performance. We will make the code and the newly collected datasets publicly available for community study.