# G-Refine: A General Quality Refiner for Text-to-Image Generation

arXiv: https://arxiv.org/abs/2404.18343 · HTML: https://mlsanity.com/paper/2404.18343/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 66 references that are in the map.
- First posted on arXiv 29 Apr 2024.

## Builds on (most cited first, 30 of 37)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting](https://mlsanity.com/paper/2112.01518/) (2021)
- [Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels](https://mlsanity.com/paper/2312.17090/) (2023)
- [Exploiting Diffusion Prior for Real-World Image Super-Resolution](https://mlsanity.com/paper/2305.07015/) (2023)
- [NIMA: Neural Image Assessment](https://mlsanity.com/paper/1709.05424/) (2017)
- [Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network](https://mlsanity.com/paper/1907.02665/) (2019)
- [Human Preference Score: Better Aligning Text-to-Image Models with Human Preference](https://mlsanity.com/paper/2303.14420/) (2023)
- [Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective](https://mlsanity.com/paper/2303.14968/) (2023)
- [DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior](https://mlsanity.com/paper/2308.15070/) (2023)
- [Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization](https://mlsanity.com/paper/2308.14469/) (2023)
- [Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision](https://mlsanity.com/paper/2309.14181/) (2023)
- [From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality](https://mlsanity.com/paper/1912.10088/) (2019)
- [FreeU: Free Lunch in Diffusion U-Net](https://mlsanity.com/paper/2309.11497/) (2023)
- [Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models](https://mlsanity.com/paper/2311.06783/) (2023)
- [Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild](https://mlsanity.com/paper/2005.13983/) (2020)
- [Towards Open-ended Visual Quality Comparison](https://mlsanity.com/paper/2402.16641/) (2024)
- [Unsupervised Real-world Image Super Resolution via Domain-distance Aware Training](https://mlsanity.com/paper/2004.01178/) (2020)
- [Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration](https://mlsanity.com/paper/2209.11345/) (2022)
- [Perceptual Video Quality Assessment: A Survey](https://mlsanity.com/paper/2402.03413/) (2024)
- [MISC: Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Model](https://mlsanity.com/paper/2402.16749/) (2024)
- [Advancing Zero-Shot Digital Human Quality Assessment through Text-Prompted Evaluation](https://mlsanity.com/paper/2307.02808/) (2023)
- [TextCraftor: Your Text Encoder Can be Image Quality Controller](https://mlsanity.com/paper/2403.18978/) (2024)
- [Active Fine-Tuning from gMAD Examples Improves Blind Image Quality Assessment](https://mlsanity.com/paper/2003.03849/) (2020)
- [Exploring the Naturalness of AI-Generated Images](https://mlsanity.com/paper/2312.05476/) (2023)
- [Q-Boost: On Visual Quality Assessment Ability of Low-level Multi-Modality Foundation Models](https://mlsanity.com/paper/2312.15300/) (2023)
- [GMS-3DQA: Projection-based Grid Mini-patch Sampling for 3D Model Quality Assessment](https://mlsanity.com/paper/2306.05658/) (2023)

## Built on by (most cited first, 8 of 8)

- [A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends](https://mlsanity.com/paper/2410.15067/) (2024)
- [R-Bench: Are your Large Multimodal Model Robust to Real-world Corruptions?](https://mlsanity.com/paper/2410.05474/) (2024)
- [ImAgent: A Unified Multimodal Agent Framework for Test-Time Scalable Image Generation](https://mlsanity.com/paper/2511.11483/) (2025)
- [VQA2: Visual Question Answering for Video Quality Assessment](https://mlsanity.com/paper/2411.03795/) (2024)
- [Image Quality Assessment: From Human to Machine Preference](https://mlsanity.com/paper/2503.10078/) (2025)
- [CCDM: Continuous Conditional Diffusion Models for Image Generation](https://mlsanity.com/paper/2405.03546/) (2024)
- [rPPG-VQA: A Video Quality Assessment Framework for Unsupervised rPPG Training](https://mlsanity.com/paper/2604.11156/) (2026)
- [From Open Loop to Closed Loop: A Test-Time Iterative Optimization Framework for Reference-Consistent Image Generation](https://mlsanity.com/paper/2607.04691/) (2026)

## Abstract (arXiv)

With the evolution of Text-to-Image (T2I) models, the quality defects of AI-Generated Images (AIGIs) pose a significant barrier to their widespread adoption. In terms of both perception and alignment, existing models cannot always guarantee high-quality results. To mitigate this limitation, we introduce G-Refine, a general image quality refiner designed to enhance low-quality images without compromising the integrity of high-quality ones. The model is composed of three interconnected modules: a perception quality indicator, an alignment quality indicator, and a general quality enhancement module. Based on the mechanisms of the Human Visual System (HVS) and syntax trees, the first two indicators can respectively identify the perception and alignment deficiencies, and the last module can apply targeted quality enhancement accordingly. Extensive experimentation reveals that when compared to alternative optimization methods, AIGIs after G-Refine outperform in 10+ quality metrics across 4 databases. This improvement significantly contributes to the practical application of contemporary T2I models, paving the way for their broader adoption. The code will be released on https://github.com/Q-Future/Q-Refine.