# Q-Ground: Image Quality Grounding with Large Multi-modality Models

arXiv: https://arxiv.org/abs/2407.17035 · HTML: https://mlsanity.com/paper/2407.17035/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 6 references that are in the map.
- First posted on arXiv 24 Jul 2024.

## Builds on (most cited first, 4 of 4)

- [Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment](https://mlsanity.com/paper/1612.01697/) (2016)
- [Learning a No-Reference Quality Metric for Single-Image Super-Resolution](https://mlsanity.com/paper/1612.05890/) (2016)
- [Exploring the Effectiveness of Video Perceptual Representation in Blind Video Quality Assessment](https://mlsanity.com/paper/2207.03723/) (2022)
- [Active Fine-Tuning from gMAD Examples Improves Blind Image Quality Assessment](https://mlsanity.com/paper/2003.03849/) (2020)

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

- [Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution](https://mlsanity.com/paper/2501.11561/) (2025)
- [Q-Insight: Understanding Image Quality via Visual Reinforcement Learning](https://mlsanity.com/paper/2503.22679/) (2025)
- [UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texture](https://mlsanity.com/paper/2512.21675/) (2025)
- [SEAGULL: No-reference Image Quality Assessment for Regions of Interest via Vision-Language Instruction Tuning](https://mlsanity.com/paper/2411.10161/) (2024)
- [Grounding-IQA: Grounding Multimodal Language Model for Image Quality Assessment](https://mlsanity.com/paper/2411.17237/) (2024)
- [Revisiting MLLM Based Image Quality Assessment: Errors and Remedy](https://mlsanity.com/paper/2511.07812/) (2025)
- [MageBench: Bridging Large Multimodal Models to Agents](https://mlsanity.com/paper/2412.04531/) (2024)
- [Scaling-up Perceptual Video Quality Assessment](https://mlsanity.com/paper/2505.22543/) (2025)
- [UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement](https://mlsanity.com/paper/2512.06750/) (2025)
- [Mitigating Perception Bias: A Training-Free Approach to Enhance LMM for Image Quality Assessment](https://mlsanity.com/paper/2411.12791/) (2024)
- [Investigate the Low-level Visual Perception in Vision-Language based Image Quality Assessment](https://mlsanity.com/paper/2512.09573/) (2025)
- [DeQA-Doc: Adapting DeQA-Score to Document Image Quality Assessment](https://mlsanity.com/paper/2507.12796/) (2025)
- [Segmenting and Understanding: Region-aware Semantic Attention for Fine-grained Image Quality Assessment with Large Language Models](https://mlsanity.com/paper/2508.07818/) (2025)
- [ViDA-UGC: Detailed Image Quality Analysis via Visual Distortion Assessment for UGC Images](https://mlsanity.com/paper/2508.12605/) (2025)
- [AgenticIQA: An Agentic Framework for Adaptive and Interpretable Image Quality Assessment](https://mlsanity.com/paper/2509.26006/) (2025)
- [Enhancing Diffusion-based Restoration Models via Difficulty-Adaptive Reinforcement Learning with IQA Reward](https://mlsanity.com/paper/2511.01645/) (2025)
- [Guiding Perception-Reasoning Closer to Human in Blind Image Quality Assessment](https://mlsanity.com/paper/2512.16484/) (2025)
- [OmniQuality-R: Advancing Reward Models Through All-Encompassing Quality Assessment](https://mlsanity.com/paper/2510.10609/) (2025)
- [Building Reasonable Inference for Vision-Language Models in Blind Image Quality Assessment](https://mlsanity.com/paper/2512.09555/) (2025)
- [Position: Evaluation of Visual Processing Should Be Human-Centered, Not Metric-Centered](https://mlsanity.com/paper/2603.00643/) (2026)
- [SR-Ground: Image Quality Grounding for Super-Resolved Content](https://mlsanity.com/paper/2605.21244/) (2026)
- [IQA-Spider: Unifying Multi-Granularity Image Quality Assessment with Reasoning, Grounding and Referring](https://mlsanity.com/paper/2605.24553/) (2026)
- [Tool-IQA: Augmenting Image Quality Assessment with Simple Tools](https://mlsanity.com/paper/2606.16082/) (2026)
- [Transformer-based Spatial Grounding: A Comprehensive Survey](https://mlsanity.com/paper/2507.12739/) (2025)
- [Understanding Pure Textual Reasoning for Blind Image Quality Assessment](https://mlsanity.com/paper/2601.02441/) (2026)
- [Panoptic Pairwise Distortion Graph](https://mlsanity.com/paper/2604.11004/) (2026)
- [IPAD-CLIP: Teaching CLIP to Detect Image Local Perceptual Artifacts](https://mlsanity.com/paper/2605.08664/) (2026)
- [Visual Distortion Detection in UGC Images Using Large Multimodal Models](https://mlsanity.com/paper/2608.09122/) (2026)
- [From Glance to Scrutiny: Progressive Distortion Reasoning for Fine-Grained Image Quality Assessment](https://mlsanity.com/paper/2609.08316/) (2026)
- [LLaVA-Assessor: Building the Foundation LMM For Visual Quality Assessment](https://mlsanity.com/paper/2609.26205/) (2026)

## Abstract (arXiv)

Recent advances of large multi-modality models (LMM) have greatly improved the ability of image quality assessment (IQA) method to evaluate and explain the quality of visual content. However, these advancements are mostly focused on overall quality assessment, and the detailed examination of local quality, which is crucial for comprehensive visual understanding, is still largely unexplored. In this work, we introduce Q-Ground, the first framework aimed at tackling fine-scale visual quality grounding by combining large multi-modality models with detailed visual quality analysis. Central to our contribution is the introduction of the QGround-100K dataset, a novel resource containing 100k triplets of (image, quality text, distortion segmentation) to facilitate deep investigations into visual quality. The dataset comprises two parts: one with human-labeled annotations for accurate quality assessment, and another labeled automatically by LMMs such as GPT4V, which helps improve the robustness of model training while also reducing the costs of data collection. With the QGround-100K dataset, we propose a LMM-based method equipped with multi-scale feature learning to learn models capable of performing both image quality answering and distortion segmentation based on text prompts. This dual-capability approach not only refines the model's understanding of region-aware image quality but also enables it to interactively respond to complex, text-based queries about image quality and specific distortions. Q-Ground takes a step towards sophisticated visual quality analysis in a finer scale, establishing a new benchmark for future research in the area. Codes and dataset are available at https://github.com/Q-Future/Q-Ground.