OpenDCVCs: A PyTorch Open Source Implementation and Performance Evaluation of the DCVC series Video Codecs
- URL: http://arxiv.org/abs/2508.04491v1
- Date: Wed, 06 Aug 2025 14:39:29 GMT
- Title: OpenDCVCs: A PyTorch Open Source Implementation and Performance Evaluation of the DCVC series Video Codecs
- Authors: Yichi Zhang, Fengqing Zhu,
- Abstract summary: We present OpenDCVCs, an open-source PyTorch implementation to advance reproducible research in learned video compression.<n>OpenDCVCs provides unified and training-ready implementations of four representative Deep Contextual Video Compression (DCVC) models.
- Score: 12.190794711534872
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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.
Related papers
- Benchmarking Conventional and Learned Video Codecs with a Low-Delay Configuration [11.016119119250765]
This paper conducts a comparative study of state-of-the-art conventional and learned video coding methods based on a low delay configuration.
To allow a fair and meaningful comparison, the evaluation was performed on test sequences defined in the AOM and MPEG common test conditions in the YCbCr 4:2:0 color space.
The evaluation results show that the JVET ECM codecs offer the best overall coding performance among all codecs tested.
arXiv Detail & Related papers (2024-08-09T12:55:23Z) - Deep Video Restoration for Under-Display Camera [98.17505013737446]
We propose a GAN-based generation pipeline to simulate the realistic UDC degradation process.
We build the first large-scale UDC video restoration dataset called PexelsUDC.
We propose a novel transformer-based baseline method that adaptively enhances degraded videos.
arXiv Detail & Related papers (2023-09-09T10:48:06Z) - VNVC: A Versatile Neural Video Coding Framework for Efficient
Human-Machine Vision [59.632286735304156]
It is more efficient to enhance/analyze the coded representations directly without decoding them into pixels.
We propose a versatile neural video coding (VNVC) framework, which targets learning compact representations to support both reconstruction and direct enhancement/analysis.
arXiv Detail & Related papers (2023-06-19T03:04:57Z) - CANF-VC: Conditional Augmented Normalizing Flows for Video Compression [81.41594331948843]
CANF-VC is an end-to-end learning-based video compression system.
It is based on conditional augmented normalizing flows (ANF)
arXiv Detail & Related papers (2022-07-12T04:53:24Z) - Efficient VVC Intra Prediction Based on Deep Feature Fusion and
Probability Estimation [57.66773945887832]
We propose to optimize Versatile Video Coding (VVC) complexity at intra-frame prediction, with a two-stage framework of deep feature fusion and probability estimation.
Experimental results on standard database demonstrate the superiority of proposed method, especially for High Definition (HD) and Ultra-HD (UHD) video sequences.
arXiv Detail & Related papers (2022-05-07T08:01:32Z) - AIVC: Artificial Intelligence based Video Codec [2.410573852722981]
AIVC is an end-to-end neural video system.
It learns to compress videos using any coding configurations.
It offers performance competitive with the recent video coder HEVC.
arXiv Detail & Related papers (2022-02-09T10:03:12Z) - Perceptual Learned Video Compression with Recurrent Conditional GAN [158.0726042755]
We propose a Perceptual Learned Video Compression (PLVC) approach with recurrent conditional generative adversarial network.
PLVC learns to compress video towards good perceptual quality at low bit-rate.
The user study further validates the outstanding perceptual performance of PLVC in comparison with the latest learned video compression approaches.
arXiv Detail & Related papers (2021-09-07T13:36:57Z) - Video Abnormal Event Detection by Learning to Complete Visual Cloze
Tests [50.1446994599891]
Video abnormal event (VAD) is a vital semi-supervised task that requires learning with only roughly labeled normal videos.
We propose a novel approach named visual cloze (VCC) which performs VAD by learning to complete "visual cloze tests" (VCTs)
We show that VCC achieves state-of-the-art VAD performance.
arXiv Detail & Related papers (2021-08-05T04:05:36Z) - OpenDVC: An Open Source Implementation of the DVC Video Compression
Method [177.67218448278143]
We introduce an open sourceflow implementation of the Deep Video Compression (DVC) method in this technical report.
MS-SSIM is the first end-to-end optimized learned video compression method, achieving better MS-SSIM performance than the Low-Delay P (LDP) very fast setting of x265.
Our OpenDVC (MS-SSIM) model provides a more convincing baseline for MS-SSIM optimized methods, which can only compare with the PSNR optimized in the past.
arXiv Detail & Related papers (2020-06-29T08:22:08Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.