Low-Bitrate Video Compression through Semantic-Conditioned Diffusion

ArXi:2512.00408v2 Announce Type: replace-cross Traditional video codecs optimized for pixel fidelity collapse at ultra-low bitrates and produce severe artifacts. This failure arises from a fundamental misalignment between pixel accuracy and human perception. We propose a semantic video compression framework named DiSCo that transmits only the most meaningful information while relying on generative priors for detail synthesis.