OpenDVC: Open Source Implementation of Deep Video Compression
Description
OpenDVC is an open-source TensorFlow implementation of the Deep Video Compression (DVC) method. It provides both PSNR-optimized and MS-SSIM-optimized models, achieving better MS-SSIM performance than the Low-Delay P (LDP) very fast setting of x265 and comparable PSNR performance. OpenDVC serves as a valuable resource for researchers and developers interested in learned video compression methods, offering pre-trained models and source codes for further development.
Resource details
- Category path
- General Tools
- Classification
- Not yet classified
OpenDVC: Open Source Implementation of Deep Video Compression is cataloged in General Tools. Its topics include video compression, deep learning, TensorFlow, PSNR, and MS-SSIM.
URL
Tags
Related resources
- Towards Practical Real-Time Neural Video Compression (DCVC-RT)CVPR 2025 paper on a neural video codec achieving 125fps at 1080p encode/decode with 21% bitrate savings versus H.266/VTM.
- 100-4K (BVI-1004K) Test Sequence Dataset100 open UHD test sequences aggregated from Netflix Chimera, UVG, SJTU, and AWS sources, cropped/normalized for ML video-coding research.
- GREEM: Measuring Energy Consumption of Video Encoding/DecodingOpen-source library for measuring energy consumption of video encoding and decoding, targeting sustainability-focused benchmarking.