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

📅 2025-08-06
📈 Citations: 0
Influential: 0
📄 PDF

career value

205K/year
🤖 AI Summary
Although the DCVC family of deep video codecs achieves state-of-the-art rate-distortion performance, its publicly available code supports only inference—severely hindering reproducibility, benchmarking, and algorithmic advancement. Method: We present the first open-source, PyTorch-based deep video compression framework that unifies end-to-end training, validation, and testing for four representative DCVC models. The framework integrates temporal modeling with hybrid entropy coding and introduces context-adaptive probability modeling to enhance compression efficiency. Contribution/Results: Comprehensive benchmarking across standard datasets demonstrates average BD-rate reductions of 15.2%–28.7% relative to HEVC. This work fills a critical gap by providing the first trainable, open-source DCVC implementation, establishing a transparent, extensible, and fully reproducible infrastructure for learning-based video coding research.

Technology Category

Application Category

📝 Abstract
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.
Problem

Research questions and friction points this paper is trying to address.

Lack of open-source PyTorch implementation for DCVC series video codecs
Limited reproducibility and benchmarking due to previous evaluation-only code releases
Need for unified framework supporting training and evaluation of DCVC models
Innovation

Methods, ideas, or system contributions that make the work stand out.

PyTorch-based open-source DCVC series implementation
Unified training-ready framework for four DCVC models
Comprehensive benchmarking with detailed documentation
🔎 Similar Papers
No similar papers found.