
Sign up to save your podcasts
Or
The paper introduces Compare2Score, a novel no-reference image quality assessment (NR-IQA) model built upon large multimodal models (LMMs). This framework addresses the challenge of converting discrete comparative image quality judgments into continuous scores, a significant hurdle in combining diverse IQA datasets. Compare2Score trains LMMs to mimic human-like visual quality comparisons by generating scaled-up comparative instructions from existing IQA datasets. It then employs an innovative soft comparison method to translate these qualitative comparisons into precise quantitative quality scores. Experiments demonstrate Compare2Score's superior generalization across various distortion types and its ability to enhance the rating accuracy of other general-purpose LMMs.
keepSave to notecopy_alldocsAdd noteaudio_magic_eraserAudio OverviewflowchartMind Maparrow_downwardJump to bottom
The paper introduces Compare2Score, a novel no-reference image quality assessment (NR-IQA) model built upon large multimodal models (LMMs). This framework addresses the challenge of converting discrete comparative image quality judgments into continuous scores, a significant hurdle in combining diverse IQA datasets. Compare2Score trains LMMs to mimic human-like visual quality comparisons by generating scaled-up comparative instructions from existing IQA datasets. It then employs an innovative soft comparison method to translate these qualitative comparisons into precise quantitative quality scores. Experiments demonstrate Compare2Score's superior generalization across various distortion types and its ability to enhance the rating accuracy of other general-purpose LMMs.
keepSave to notecopy_alldocsAdd noteaudio_magic_eraserAudio OverviewflowchartMind Maparrow_downwardJump to bottom