DeepField-PQO
AI technology is used to preprocess the input video in order to increase the compression efficiency of the codec while preserving video quality.
DeepField
It is an AI-powered Super Resolution technology that upscales videos to high resolution and improves video quality by using temporal and spatial information.
Optimize video pixels
to improve encoding efficiency
It is an artificial intelligence model trained in consideration of the encoding process so that there is no perceived quality degradation by viewers, but video compression efficiency can be improved.
It works with any codec and improves compression efficiency.
If replacing with the next-generation compression codec is impractical owing to increased computing infrastructure costs, it can be applied to the existing codec, lowering the cost of storage and network by 30% on average.
Product features
Perceptual video quality optimization
The pretrained AI model enhances the details of areas that affect human perception quality while decreasing the details of minor areas. It reduces the amount of data required for video compression while maintaining perceptual video quality.
How we deliver the product
SDK
Provided as an SDK optimized for GPU/FPGA accelerator cards and supports the FFmpeg framework, making it simple to integrate into your media workflow.
Silicon IP
The product is also available as Semiconductor IP that can be integrated into media processing FPGAs or ASICs for servers for optimal performance.
UI Service
Offers file-based video upscaling cloud service for content providers.
Supported Devices / Supported Platforms
On premises
Nvidia GPU Card, Xilinx ALVEO FPGA Card
Cloud
AWS EC2 instances, MS Azure NP instances
Inquiry For more information,
please contact us.