Pulsar-VMAF
It measures VMAF, a video quality metric, faster than open source.
Pulsar
It is an AI-powered Super Resolution technology that upscales videos to high resolution and improves video quality by using temporal and spatial information.
Very fast
VMAF accelerator
There is an increasing need to measure video quality on a human subjective (perceptual) level. Although Netflix's VMAF is extensively used, its large computational load places a strain on computer expenses and processing time.
BLUEDOT lowers the cost burden since it develops a VMAF-specific accelerator using semiconductor design techniques.
Product features
VMAF becoming widely used metric
Service Providers try to find the optimal combination(bit rate, resolution) for each video or shot so as to save storage and network costs while improving the user's viewing experience. Encoding and VMAF quality measuring must be done dozens of times to find the optimal combination, which necessitates a significant amount of computation resources. By leveraging BLUEDOT's semiconductor design technology, you can speed up VMAF quality measurements and reduce computing costs.
Pulsar-VMAF Performance
FPGA-accelerated VMAF is x4 faster than CPU-based open source and x3 lower in compute costs.
How we deliver the product
SDK
Provided as an SDK optimized for FPGA accelerator cards and as it runs under 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.
Supported Devices / Supported Platforms
Pulsar-VMAF is implemented into Silicon IP optimal for AMD/Xilinx FPGAs.
On premises
Xilinx ALVEO U50, U55c CARD
Cloud
MS Azure NP10 instances, AWS EC2 f1 instances
Inquiry For more information,
please contact us.