4 papers · 1 filter
GVCCTurbo: Rate-Compute Quality Scheduling for Codebook Driven Generative Compression
Ziyue Zeng, Dingjie Peng, Xun Su +1
Codebook-driven generative compression uses a pretrained image or video generator as a zero-shot visual prior and transmits compact codebook indices to guide reconstruction at ultr…
GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow
Ziyue Zeng, Xun Su, Haoyuan Liu +3
At ultra-low bitrates, high-fidelity reconstruction requires sampling plausible videos from the posterior rather than regressing to oversmoothed conditional means. We propose Gener…
Seed Selection for Human-Oriented Image Reconstruction via Guided Diffusion
Yui Tatsumi, Ziyue Zeng, Hiroshi Watanabe
Conventional methods for scalable image coding for humans and machines require the transmission of additional information to achieve scalability. A recent diffusion-based approach…
Time Step Generating: A Universal Synthesized Deepfake Image Detector
Ziyue Zeng, Haoyuan Liu, Dingjie Peng +2
Currently, high-fidelity text-to-image models are developed in an accelerating pace. Among them, Diffusion Models have led to a remarkable improvement in the quality of image gener…