SageIQ: Scene-Graph-Guided Blind Image Quality Assessment
Conventional Blind Image Quality Assessment (BIQA) methods typically assess the entire image quality, which is suboptimal for tasks like autonomous driving that concern specific Task-Aligned Region (TAR). Moreover, we observe that advanced Multimodal Large Language Model (MLLM)-based BIQA models exhibit bias when evalu...
Ren-Wei Yang, Zheng-Jie Yang, Yun Wang et al.
· IEEE Transactions on Emergin... · 0 citations