CSFlow: Aligning Flow Matching with Human Contrast Sensitivity
Researchers have developed CSFlow, a novel weighting scheme that aligns the iterative denoising process in flow matching models with human contrast sensitivity. This method accounts for the human visual system's varying sensitivity to different spatial frequencies and the tendency of diffusion models to stabilize coarse image content before fine details. By estimating which frequencies are generated at each reverse flow interval and weighting timesteps accordingly, CSFlow has demonstrated improvements in image generation quality, reducing FID scores and enhancing visual realism. AI
IMPACT Improves realism and quality of generated images by incorporating human visual perception into the generation process.