Q-Refine：用於人工智慧生成圖像的知覺質量精煉器
Q-Refine: A Perceptual Quality Refiner for AI-Generated Image
January 2, 2024
作者: Chunyi Li, Haoning Wu, Zicheng Zhang, Hongkun Hao, Kaiwei Zhang, Lei Bai, Xiaohong Liu, Xiongkuo Min, Weisi Lin, Guangtao Zhai
cs.AI
摘要
近年來，隨著文本轉圖像（T2I）模型的快速演進，其生成結果的不理想性已成為一個挑戰。然而，對不同質量的人工智慧生成圖像（AIGIs）進行統一的優化不僅限制了對低質量AIGIs的優化能力，還對高質量AIGIs帶來了負面影響。為了解決這個問題，提出了一種名為Q-Refine的質量獎勵精煉器。基於人類視覺系統（HVS）的偏好，Q-Refine首次使用圖像質量評估（IQA）指標來引導精煉過程，並通過三個自適應管道修改不同質量的圖像。實驗表明，對於主流T2I模型，Q-Refine能夠有效優化不同質量的AIGIs。它可以成為一個通用的精煉器，從忠實度和美學質量兩個層面優化AIGIs，從而擴展T2I生成模型的應用。
English
With the rapid evolution of the Text-to-Image (T2I) model in recent years,
their unsatisfactory generation result has become a challenge. However,
uniformly refining AI-Generated Images (AIGIs) of different qualities not only
limited optimization capabilities for low-quality AIGIs but also brought
negative optimization to high-quality AIGIs. To address this issue, a
quality-award refiner named Q-Refine is proposed. Based on the preference of
the Human Visual System (HVS), Q-Refine uses the Image Quality Assessment (IQA)
metric to guide the refining process for the first time, and modify images of
different qualities through three adaptive pipelines. Experimental shows that
for mainstream T2I models, Q-Refine can perform effective optimization to AIGIs
of different qualities. It can be a general refiner to optimize AIGIs from both
fidelity and aesthetic quality levels, thus expanding the application of the
T2I generation models.