Thoughts on generative models, video quality, and the intersection of perception and computation.
A deep dive into rectified flow models and how they enable faster, more efficient generation compared to traditional diffusion models. We'll explore the mathematical foundations and practical implementations.
Read more →Why measuring quality in high dynamic range videos is fundamentally different from SDR, and what makes it one of the most challenging problems in perceptual quality research.
Read more →A practical guide to implementing CFG++ and its rectified variant for improved image generation with flow-based models.
Read more →