arXiv Computer Vision By Jiancheng Zhao, Jixiang Luo, Haibin Huang, Chi Zhang, Xuelong Li

Towards Practical 20 kbps Generative Video Compression via Adaptive Tokenization and Entropy Modeling

Read the original on arXiv Computer Vision →

arXiv:2611. 08099v1 Announce Type: new Abstract: Video compression at ultra-low bitrates remains challenging due to the loss of perceptually important details under limited bit budgets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv Computer Vision
6d ago

When to Start Denoising? Adaptive Denoising Entry for Generative Video Compression

The paper introduces ADE-GVC, a generative video compression framework that adaptively selects the denoising start timestep in diffusion models to balance reconstruction fidelity and perceptual realism. It uses a lightweight predictor to estimate the optimal start point from compressed latents and a temporal adapter to inject compression-aware conditions into a pretrained diffusion model. Experiments show ADE‑GVC outperforms existing methods, achieving significant bitrate savings and improved perceptual quality.

By Zifu Zhang, Yuqiao Li, Ding Ding, Shengxi Li, Mai Xu, Daowen Li, Kai Li, Ying Chen
arXiv Computer Vision
Oct 23

ResGVC: Residual Coding for High-fidelity Generative Video Compression

ResGVC introduces a residual coding framework for generative video compression that transmits residual signals to guide denoising directly in pixel space. The method encodes original frames with a learned video codec, decomposes the reconstruction error into residual segments at each denoising step, and compresses these segments using a residual codec powered by a diffusion transformer entropy model. Compared to prior state‑of‑the‑art methods, ResGVC achieves significant BD‑rate reductions—63.7% for LPIPS and 83.8% for PSNR—while delivering superior visual quality.

By Ding Ding, Daowen Li, Ying Chen, Kai Li
arXiv AI
Sep 28

GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow

The paper introduces GVCC, a zero‑shot video compression framework that uses a pretrained generative video model as the decoder. GVCC transforms deterministic rectified‑flow samplers into stochastic processes, enabling the transmission of compressed information through per‑step stochastic innovations. The authors evaluate three GVCC variants—Text‑to‑Video, Image‑to‑Video, and First‑Last‑Frame‑to‑Video—on the UVG dataset, reporting perceptual, fidelity, and temporal metrics without claiming global rate‑distortion gains.

By Ziyue Zeng, Xun Su, Haoyuan Liu, Bingyu Lu, Yui Tatsumi, Hiroshi Watanabe