arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2508.04491eess.IVcs.CV
收藏

OpenDCVCs:DCVC系列视频编解码器的PyTorch开源实现与性能评估

OpenDCVCs: A PyTorch Open Source Implementation and Performance Evaluation of the DCVC series Video Codecs

Purdue University West Lafayette, USA(帕克大学西拉法叶分校)

Yichi Zhang, Fengqing Zhu

AI总结:

OpenDCVCs是一个开源PyTorch框架,统一实现了四种DCVC视频压缩模型,支持端到端训练与评估,提供文档和基准测试结果,以促进可复现研究。

摘要:

我们提出了OpenDCVCs,这是一个开源PyTorch实现,旨在推进学习型视频压缩领域的可复现研究。OpenDCVCs提供了四种代表性深度上下文视频压缩(DCVC)模型的统一且可训练的实现——DCVC、带时间上下文建模的DCVC(DCVC-TCM)、带混合熵建模的DCVC(DCVC-HEM)以及带多样上下文的DCVC(DCVC-DC)。尽管DCVC系列在比特率降低方面相对于经典编解码器和先进学习模型取得了显著成效,但以往公开代码发布仅限于评估代码,这给可复现性、基准测试和进一步开发带来了重大障碍。OpenDCVCs通过提供一个全面、自包含的框架来弥合这一差距,该框架支持所有包含算法的端到端训练和评估。该实现包括详细文档、评估协议以及跨多个数据集的广泛基准测试结果,为比较和扩展提供了透明且一致的基石。所有代码和实验工具均可公开获取,网址为https://gitlab.com/viper-purdue/opendcvcs,从而赋能社区加速研究并促进协作。

英文摘要:

We present OpenDCVCs, an open-source PyTorch implementation designed to advance reproducible research in learned video compression. OpenDCVCs provides unified and training-ready implementations of four representative Deep Contextual Video Compression (DCVC) models--DCVC, DCVC with Temporal Context Modeling (DCVC-TCM), DCVC with Hybrid Entropy Modeling (DCVC-HEM), and DCVC with Diverse Contexts (DCVC-DC). While the DCVC series achieves substantial bitrate reductions over both classical codecs and advanced learned models, previous public code releases have been limited to evaluation codes, presenting significant barriers to reproducibility, benchmarking, and further development. OpenDCVCs bridges this gap by offering a comprehensive, self-contained framework that supports both end-to-end training and evaluation for all included algorithms. The implementation includes detailed documentation, evaluation protocols, and extensive benchmarking results across diverse datasets, providing a transparent and consistent foundation for comparison and extension. All code and experimental tools are publicly available at https://gitlab.com/viper-purdue/opendcvcs, empowering the community to accelerate research and foster collaboration.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑