Dimensions overall score 8.0

GitHub Code Pulse

No public code linked for this paper yet.

• Existing generative model evaluations using feature-distribution metrics like FID discard cues critical for perceptual quality.limitation 95%
• Modern 1D image tokenizers compactly encode both semantic and perceptual information in discrete visual tokens.technical 95%
• Codebook Histogram Distance (CHD) is a training-free distribution metric in token space.method 95%
• Code Mixture Model Score (CMMS) is a no-reference quality metric learned from synthetic degradations of token sequences.method 95%
• VisForm is a benchmark comprising 210K images across 62 visual forms and 12 generative models.method 95%
• The proposed token-based metrics (CHD and CMMS) achieve state-of-the-art correlation with human judgments on AGIQA, HPDv2/3, and VisForm benchmarks.result 95%
• The authors will release all code and datasets to facilitate future research.method 95%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card