arXiv Computer Vision

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

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.

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
Hugging Face Trending Papers
Aug 13

V-RAE: Rethinking Video Latent Spaces for Generation

Latent video generation relies on autoencoders to define a compact space in which generative models operate. Although video autoencoder architectures have evolved substantially, their latent spaces are still optimized primarily for pixel-level reconstruction and provide limited high-level semantic organization.

arXiv Computer Vision
Oct 12

Unified Generative Video Compression with Autoregressive and Bidirectional Video Diffusion

The paper introduces UniGVC, a unified generative video codec that supports both low‑delay streaming and high‑quality playback from a single bitstream. It offers two decoding modes: UniGVC‑BI, a bidirectional diffusion model with dense attention for quality‑oriented random‑access decoding, and UniGVC‑AR, a windowed autoregressive diffusion model for low‑delay streaming. Both modes share a hierarchical latent codec that produces ultra‑low‑bitrate conditions, enabling the BI model to act as a teacher for distilling the AR model, while a lightweight conditional decoder further reduces streaming latency.

By Tianyu Zhang, Shuai Huo, Dengchao Jin, Hewei Liu, Meng Lei, Tianwen Wu, Jiawen Gu, Chao Zhou, Li Li, Dong Liu
arXiv AI
Sep 4

LRConv-NeRV: Low Rank Convolution for Efficient Neural Video Compression

LRConv-NeRV introduces low‑rank separable convolutions into the NeRV neural video decoder, replacing selected dense 3x3 layers to reduce computational load and memory usage. By applying low‑rank factorization progressively from the largest to earlier decoder stages, the method offers controllable trade‑offs between reconstruction quality and efficiency. Experiments show that applying LRConv only to the final decoder stage cuts decoder complexity by 68% and model size by 9.3% with negligible quality loss, while INT8 quantization preserves performance close to the dense baseline.

By Tamer Shanableh
Hugging Face Trending Papers
Aug 3

CRAFT: Compression via Recursive Adaptive Fusion of Video Tokens for Vision-Language Models

In video understanding, vision-language models (VLMs) must ingest massive numbers of visual tokens, causing the computational and memory cost of the prefill stage to rise sharply. Such visual sequences are highly redundant along the spatio-temporal dimension, yet a high compression ratio is often accompanied by the loss of critical details.