Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language Model

• URL: http://arxiv.org/abs/2503.06141v1
• Date: Sat, 08 Mar 2025 09:49:10 GMT
• Title: Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language Model
• Authors: Mingxing Li, Rui Wang, Lei Sun, Yancheng Bai, Xiangxiang Chu,
• Abstract summary: Large language models (MLLMs) have shown great potential in image quality assessment (IQA) and image aesthetic assessment (IAA)<n>Here, we introduce a novel dataset, named Realistic image Quality and Aesthetic (RealQA)<n>These attributes span three levels: low level (e.g., image clarity), middle level (e.g., subject integrity) and high level (e.g. composition)<n>Surprisingly, by predicting just two extra significant digits, the next token paradigm can achieve SOTA performance.
• Score: 19.2881640541533
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid expansion of mobile internet has resulted in a substantial increase in user-generated content (UGC) images, thereby making the thorough assessment of UGC images both urgent and essential. Recently, multimodal large language models (MLLMs) have shown great potential in image quality assessment (IQA) and image aesthetic assessment (IAA). Despite this progress, effectively scoring the quality and aesthetics of UGC images still faces two main challenges: 1) A single score is inadequate to capture the hierarchical human perception. 2) How to use MLLMs to output numerical scores, such as mean opinion scores (MOS), remains an open question. To address these challenges, we introduce a novel dataset, named Realistic image Quality and Aesthetic (RealQA), including 14,715 UGC images, each of which is annoted with 10 fine-grained attributes. These attributes span three levels: low level (e.g., image clarity), middle level (e.g., subject integrity) and high level (e.g., composition). Besides, we conduct a series of in-depth and comprehensive investigations into how to effectively predict numerical scores using MLLMs. Surprisingly, by predicting just two extra significant digits, the next token paradigm can achieve SOTA performance. Furthermore, with the help of chain of thought (CoT) combined with the learnt fine-grained attributes, the proposed method can outperform SOTA methods on five public datasets for IQA and IAA with superior interpretability and show strong zero-shot generalization for video quality assessment (VQA). The code and dataset will be released.

Related papers

• Q-Insight: Understanding Image Quality via Visual Reinforcement Learning [27.26829134776367]
  Image quality assessment (IQA) focuses on the perceptual visual quality of images, playing a crucial role in downstream tasks such as image reconstruction, compression, and generation. We propose Q-Insight, a reinforcement learning-based model built upon group relative policy optimization (GRPO) We show that Q-Insight substantially outperforms existing state-of-the-art methods in both score regression and degradation perception tasks.
  arXiv  Detail & Related papers  (2025-03-28T17:59:54Z)
• M3-AGIQA: Multimodal, Multi-Round, Multi-Aspect AI-Generated Image Quality Assessment [65.3860007085689]
  M3-AGIQA is a comprehensive framework for AGI quality assessment.<n>It includes a structured multi-round evaluation mechanism, where intermediate image descriptions are generated.<n>Experiments conducted on multiple benchmark datasets demonstrate that M3-AGIQA achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-02-21T03:05:45Z)
• Q-Ground: Image Quality Grounding with Large Multi-modality Models [61.72022069880346]
  We introduce Q-Ground, the first framework aimed at tackling fine-scale visual quality grounding. Q-Ground combines large multi-modality models with detailed visual quality analysis. Central to our contribution is the introduction of the QGround-100K dataset.
  arXiv  Detail & Related papers  (2024-07-24T06:42:46Z)
• UniQA: Unified Vision-Language Pre-training for Image Quality and Aesthetic Assessment [23.48816491333345]
  Image Quality Assessment (IQA) and Image Aesthetic Assessment (IAA) aim to simulate human subjective perception of image visual quality and aesthetic appeal. Existing methods typically address these tasks independently due to distinct learning objectives. We propose Unified vision-language pre-training of Quality and Aesthetics (UniQA) to learn general perceptions of two tasks, thereby benefiting them simultaneously.
  arXiv  Detail & Related papers  (2024-06-03T07:40:10Z)
• Descriptive Image Quality Assessment in the Wild [25.503311093471076]
  VLM-based Image Quality Assessment (IQA) seeks to describe image quality linguistically to align with human expression. We introduce Depicted image Quality Assessment in the Wild (DepictQA-Wild) Our method includes a multi-functional IQA task paradigm that encompasses both assessment and comparison tasks, brief and detailed responses, full-reference and non-reference scenarios.
  arXiv  Detail & Related papers  (2024-05-29T07:49:15Z)
• Large Multi-modality Model Assisted AI-Generated Image Quality Assessment [53.182136445844904]
  We introduce a large Multi-modality model Assisted AI-Generated Image Quality Assessment (MA-AGIQA) model. It uses semantically informed guidance to sense semantic information and extract semantic vectors through carefully designed text prompts. It achieves state-of-the-art performance, and demonstrates its superior generalization capabilities on assessing the quality of AI-generated images.
  arXiv  Detail & Related papers  (2024-04-27T02:40:36Z)
• Multi-Modal Prompt Learning on Blind Image Quality Assessment [65.0676908930946]
  Image Quality Assessment (IQA) models benefit significantly from semantic information, which allows them to treat different types of objects distinctly. Traditional methods, hindered by a lack of sufficiently annotated data, have employed the CLIP image-text pretraining model as their backbone to gain semantic awareness. Recent approaches have attempted to address this mismatch using prompt technology, but these solutions have shortcomings. This paper introduces an innovative multi-modal prompt-based methodology for IQA.
  arXiv  Detail & Related papers  (2024-04-23T11:45:32Z)
• Q-Bench+: A Benchmark for Multi-modal Foundation Models on Low-level Vision from Single Images to Pairs [71.07108539262721]
  We design benchmark settings to emulate human language responses related to low-level vision. We extend the low-level perception-related question-answering and description evaluations of MLLMs from single images to image pairs. We demonstrate that several MLLMs have decent low-level visual competencies on single images, but only GPT-4V exhibits higher accuracy on pairwise comparisons than humans.
  arXiv  Detail & Related papers  (2024-02-11T06:44:11Z)
• Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs [49.88461345825586]
  This paper proposes a new framework to enhance the fine-grained image understanding abilities of MLLMs. We present a new method for constructing the instruction tuning dataset at a low cost by leveraging annotations in existing datasets. We show that our model exhibits a 5.2% accuracy improvement over Qwen-VL and surpasses the accuracy of Kosmos-2 by 24.7%.
  arXiv  Detail & Related papers  (2023-10-01T05:53:15Z)
• Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild [38.197794061203055]
  We propose a Mixture of Experts approach to train two separate encoders to learn high-level content and low-level image quality features in an unsupervised setting. We deploy the complementary low and high-level image representations obtained from the Re-IQA framework to train a linear regression model. Our method achieves state-of-the-art performance on multiple large-scale image quality assessment databases.
  arXiv  Detail & Related papers  (2023-04-02T05:06:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.