Q-Boost: On Visual Quality Assessment Ability of Low-level Multi-Modality Foundation Models
This addresses the problem of visual quality assessment for low-level vision tasks, but it is incremental as it builds on existing MLLM capabilities.
The paper tackles the limited exploration of Multi-modality Large Language Models (MLLMs) in visual quality assessment by introducing Q-Boost, a strategy that enhances low-level MLLMs for image and video quality assessment tasks, resulting in outstanding zero-shot performance.
Recent advancements in Multi-modality Large Language Models (MLLMs) have demonstrated remarkable capabilities in complex high-level vision tasks. However, the exploration of MLLM potential in visual quality assessment, a vital aspect of low-level vision, remains limited. To address this gap, we introduce Q-Boost, a novel strategy designed to enhance low-level MLLMs in image quality assessment (IQA) and video quality assessment (VQA) tasks, which is structured around two pivotal components: 1) Triadic-Tone Integration: Ordinary prompt design simply oscillates between the binary extremes of $positive$ and $negative$. Q-Boost innovates by incorporating a `middle ground' approach through $neutral$ prompts, allowing for a more balanced and detailed assessment. 2) Multi-Prompt Ensemble: Multiple quality-centric prompts are used to mitigate bias and acquire more accurate evaluation. The experimental results show that the low-level MLLMs exhibit outstanding zeros-shot performance on the IQA/VQA tasks equipped with the Q-Boost strategy.