Learning Scene-invariant Distribution for Generalizable Blind Image Quality Assessment

The inherent diversity of visual scenes poses a fundamental challenge in blind image quality assessment (BIQA), which has become a major obstacle to the model generalization. In this study, we found that human annotations for images with different visual scenes exhibit distinct quality distribution discrepancies. The existing BIQA models tend to overfit to such diversified distributions, which in turn leads to compromised model generalizability, especially when dealing with unseen scenes in the real-world scenario. Motivated by the above facts, this paper presents a generalizable BIQA model by learning Scene-INvariant Distribution, named SIND. Specifically, we propose a distribution alignment framework to alleviate the distribution discrepancy for quality regression models, which is achieved by automatically scaling and shifting the cross-scene distributions into a unified distribution. Then, the aligned unified distribution is leveraged to supervise the model training, achieving scene-invariant and quality-aware feature representation. In addition, a token-complementary patch reasoning network is designed to extract comprehensive quality-aware features from both the image overview and detail, achieving more accurate quality prediction. Extensive experiments for both image technical- and aesthetic-quality assessment tasks show the superiority of the proposed SIND model over the state-of-the-arts. Moreover, the proposed framework is model-agnostic and can enhance model generalizability without incurring extra inference costs. The proposed method won the championship in the NTIRE 2024 Portrait Quality Assessment Challenge. Codes will be available at https://github.com/ZachL1/SIND.