Comprehensive Blind Assessment of AI-Generated Image Quality: Evaluating Visual Quality, Authenticity, and Content Consistency

The proposed AMFF-Net comprehensively evaluates the quality of AI-generated images (AGIs) from three dimensions: visual quality, authenticity, and content consistency. It utilizes a multi-scale input strategy and an adaptive feature fusion block to capture both local and global image details, and compares the semantic features between the text prompt and generated image to assess content consistency.