'Meridian': Why Netflix Is Helping Competitors with Content and Code (2016)
Netflix created "Meridian," a 12-minute film for testing video codecs on 4K TVs. Shared under a Creative Commons license, it aids industry collaboration and promotes open source practices in Hollywood.
Read original article
"Meridian" is a 12-minute Netflix original program created not for its subscribers but for algorithms and programmers. The film serves as test footage to evaluate video codecs and streaming performance on 4K TVs. Netflix is sharing "Meridian" under a Creative Commons license to aid hardware manufacturers, codec developers, and even competitors like Amazon and Hulu. Additionally, Netflix is open-sourcing tools to address challenges in managing multiple versions of movies for different markets, languages, and content requirements. The company aims to streamline this process using the Interoperable Master Format (IMF) standard, enhancing collaboration in the industry. By releasing tools and projects like VMAF and "Meridian," Netflix is promoting open source practices in Hollywood, similar to its initiatives in cloud computing. Despite being algorithm-focused, "Meridian" is available for Netflix subscribers to enjoy, showcasing advanced visuals and serving as a unique addition to the platform's content catalog.
Related
Video annotator: a framework for efficiently building video classifiers
The Netflix Technology Blog presents the Video Annotator (VA) framework for efficient video classifier creation. VA integrates vision-language models, active learning, and user validation, outperforming baseline methods with an 8.3 point Average Precision improvement.
Generating audio for video
Google DeepMind introduces V2A technology for video soundtracks, enhancing silent videos with synchronized audio. The system allows users to guide sound creation, aligning audio closely with visuals for realistic outputs. Ongoing research addresses challenges like maintaining audio quality and improving lip synchronization. DeepMind prioritizes responsible AI development, incorporating diverse perspectives and planning safety assessments before wider public access.
HybridNeRF: Efficient Neural Rendering
HybridNeRF combines surface and volumetric representations for efficient neural rendering, achieving 15-30% error rate improvement over baselines. It enables real-time framerates of 36 FPS at 2K×2K resolutions, outperforming VR-NeRF in quality and speed on various datasets.
Netflix's bet on advanced video encoding
Anne Aaron, Netflix's senior encoding technology director, drives bandwidth savings and quality improvements through innovative encoding methods like per-title encoding and machine learning models. Netflix's commitment to optimizing streaming quality remains strong.
Microsoft shelves its underwater data center
Microsoft has ended its underwater data center experiment, noting improved server longevity underwater. Despite success, Microsoft shifts focus to other projects like AI supercomputers and nuclear ambitions, discontinuing further underwater endeavors.
4 commentshttps://netflixtechblog.com/introducing-svt-av1-a-scalable-o...
https://netflixtechblog.com/svt-av1-an-open-source-av1-encod...
SVT-AV1 has since been adopted by AOMedia:
https://gitlab.com/AOMediaCodec/SVT-AV1
With SVT-AV1 you can achieve encode times similar to x264, x265, and libvpx by choosing the right preset and still achieve better image quality. See the "computation trade-offs" graph in this blog post:
https://engineering.fb.com/2023/02/21/video-engineering/av1-...
SVT-AV1 2.1 is the latest release with still more performance improvements:
[1] https://www.statista.com/outlook/dmo/digital-media/video-on-...
Related
Video annotator: a framework for efficiently building video classifiers
The Netflix Technology Blog presents the Video Annotator (VA) framework for efficient video classifier creation. VA integrates vision-language models, active learning, and user validation, outperforming baseline methods with an 8.3 point Average Precision improvement.
Generating audio for video
Google DeepMind introduces V2A technology for video soundtracks, enhancing silent videos with synchronized audio. The system allows users to guide sound creation, aligning audio closely with visuals for realistic outputs. Ongoing research addresses challenges like maintaining audio quality and improving lip synchronization. DeepMind prioritizes responsible AI development, incorporating diverse perspectives and planning safety assessments before wider public access.
HybridNeRF: Efficient Neural Rendering
HybridNeRF combines surface and volumetric representations for efficient neural rendering, achieving 15-30% error rate improvement over baselines. It enables real-time framerates of 36 FPS at 2K×2K resolutions, outperforming VR-NeRF in quality and speed on various datasets.
Netflix's bet on advanced video encoding
Anne Aaron, Netflix's senior encoding technology director, drives bandwidth savings and quality improvements through innovative encoding methods like per-title encoding and machine learning models. Netflix's commitment to optimizing streaming quality remains strong.
Microsoft shelves its underwater data center
Microsoft has ended its underwater data center experiment, noting improved server longevity underwater. Despite success, Microsoft shifts focus to other projects like AI supercomputers and nuclear ambitions, discontinuing further underwater endeavors.