开源4个视频压缩模型，支持训练与评测，提升可复现性。
OpenDCVCs: A PyTorch Open Source Implementation and Performance Evaluation of the DCVC series Video Codecs
- 基于PyTorch统一实现4个深度上下文视频压缩模型。
- 提供完整训练流程与跨数据集基准测试结果。
- 适合想复现或改进视频压缩算法的研究者使用。
我们提出OpenDCVCs，一个基于PyTorch的开源实现，旨在推动学习型视频压缩的可复现研究。该框架统一提供了四个代表性深度上下文视频压缩（DCVC）模型——DCVC、DCVC-TCM（带时序建模）、DCVC-HEM（混合熵建模）、DCVC-DC（多样上下文）的训练就绪版本。尽管DCVC系列在比特率上显著优于传统编码器和先进学习模型，但此前公开代码仅限于评估代码，严重阻碍了可复现性、基准对比与进一步开发。OpenDCVCs通过提供自包含的完整框架，支持所有算法的端到端训练与评估。实现包含详细文档、评估协议及多数据集上的广泛基准结果，为比较与扩展提供透明一致的基础。所有代码与实验工具已公开于https://gitlab.com/viper-purdue/opendcvcs，助力社区加速研究与协作。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。