Tag: NVIDIA

4K TVAOM AV1Content-AdaptiveIBCLiveNVIDIA

Live 4Kp60 Optimized Encoding with Beamr CABR and NVIDIA Holoscan for Media

Posted on by Tamar Shoham

This year at IBC 2024 in Amsterdam, we are excited to demonstrate Live 4K p60 optimized streaming with our Content-Adaptive Bitrate (CABR) technology on NVIDIA Holoscan for Media, a software-defined, AI-enabled platform that allows live video pipelines to run on the same infrastructure as AI. Using the CABR GStreamer plugin, premiered at the NAB Show earlier this year, we now support live, quality-driven optimized streaming for 4Kp60 video content.

It is no secret that savvy viewers are coming to expect the high-quality experience of 4K Ultra-High-Definition streamed at 60 frames per second for premium events. What started with a drizzle a few years back has become the high end norm for recent events such as the 2024 Olympics, where techies were sharing insights on where it could be accessed.

Given the fact that 4K means a whopping four times the pixels compared to full HD resolution, keeping up with live encoding of 4K at 60 fps can be quite challenging, and can also result in bitrates that are too high to manage.

One possible solution for broadcasters is to encode and transmit at 1080p and rely on the constantly improving upscalers available on TVs to provide the 4K experience, but this of course means they cannot control the user experience. A better solution is to have a platform that is super fast, and can create live 4Kp60 encodes, which combine excellent quality with an optimization process that minimizes the required bitrate for transmission.

Comparison of 4K Live video before and after optimization

Beamr CABR on Holoscan for Media offers exactly that, by combining the fast data buses and easy-to-use architecture of Holoscan for Media with Beamr hardware-accelerated, quality-driven optimized AV1 encoding. Together, it is possible to stream super efficient, 4K, lower bitrate encodes at top notch quality.

Content Adaptive Bitrate encoding, or CABR, is Beamr’s patented and award-winning technology that uses a quality measure to select the best candidate with the lowest bitrate and the same perceptual quality as a reference frame. In other words, users can enjoy 30-50% lower bitrate, faster delivery of files or live video streams and improved user experience – all with exactly the same quality as the original video.

In order to achieve aggressive bitrates which are feasible for broadcast of live events, we configure the system to use AV1 encoding. The advanced AV1 format has been around since 2018. However, its full potential has not been fully realized by many players in the video arena. AV1 is raising the bar significantly in comparison to previous modern codecs, such as AVC (H.264) or HEVC (H.265), in terms of efficiency, performance with GPUs and high quality for real-time video. When combined with CABR – AV1 is offering up even more. According to our tests, AV1 can reduce data by 50% compared to AVC and by 30% compared to HEVC. We also showed that CABR optimized AV1 is beneficial for machine learning tasks.

Putting all three of these technologies together, namely deploying Holoscan for Media with the Beamr CABR solution inside, which in turn is using NVIDIA’s hardware-accelerated AV1 encoder, provides a platform that offers spectacular benefits. With the rise in demand for high-quality live streaming at high resolution, high fps and manageable bitrates, while keeping an eye on the encoding costs – this solution is definitely an interesting prospect for companies looking to boost their streaming workflows.

AIAOM AV1cabrNVIDIAOracle Cloud Infrastructure (OCI)

Beamr Now Offering Oracle Cloud Infrastructure Customers 30% Faster Video Optimization

Posted on by Tamar Shoham

Beamr’s Content Adaptive Bit Rate solution enables significantly decreasing video file size or bitrates without changing the video resolution or compromising perceptual quality. Since the optimized file is fully standard compliant, it can be used in your workflow seamlessly, whatever your use case, be it video streaming, playback or even part of an AI workflow.

Beamr first launched Beamr cloud earlier this year, and we are now super excited to announce that our valued partnership with Oracle Cloud Infrastructure (OCI) is enabling us to offer to OCI customers more features and better performance.

The performance improvements are due in part to the availability of the powerful NVIDIA L40S GPUs on OCI. In preliminary testing we found that running our video encoding workflows can be up to 30% faster when using these cards, than when running on the cards we currently use in the Beamr Cloud solution.

This was derived from testing AVC and HEVC NVENC driven encodes for a set of nine 1080p classic test clips with eight different configurations, and comparing encoding wall times on an A10G vs. a L40S GPU. Speedup factors of up to 55% were observed, with an average just above 30%. The full test data is available here.

Another exciting feature about these cards is that they support AV1 encoding, which means Beamr Cloud will now offer to turn your videos into optimized AV1 encodes, offering even higher bitrate/file size savings.

What’s the fuss about AV1?

In order to store and transmit video, substantial compression is needed. From the very earliest efforts to standardize video compression in the 90s, there has been a constant effort to create video compression standards offering increasing efficiency – meaning that the same video quality can be achieved with smaller files or lower bitrates.

As shown in the schematic illustration below, AV1 has come a long way in improving over H.264/AVC, the most widely adopted standard today, despite being 20 years old. However, the increased compression efficiency is not free – the computational complexity of newer codecs is also significantly higher, motivating the adoption of hardware accelerated encoding options.

With the demand and need for Video AI workflows continuing to rise, the ability to perform fully automatic, fast, efficient, optimized video encoding is an important enabler.

The Beamr GPU powered video compression and optimization occur within the GPU on OCI, right at the heart of these AI workflows, making them extremely well placed to offer benefits to such workflows. We have previously shown in a number of case studies that there is no negative impact on inference or training results when using the optimized files – making the integration of this optimization process into AI workflows a natural choice for cost savvy developers.

AOM AV1BroadcastcabrContent-AdaptiveLiveNVIDIA

Real-time Video Optimization with Beamr CABR and NVIDIA Holoscan for Media

Posted on by Dan Julius

This year at the NAB Show 2024 in Las Vegas, we are excited to demonstrate our Content-Adaptive Bitrate (CABR) technology on the NVIDIA Holoscan for Media platform. By implementing CABR as a GStreamer plugin, we have, for the first time, made bitrate optimization of live video streams easily achievable in the cloud or premise.

Building on the NVIDIA DeepStream software development kit, which can extends GStreamer’s capabilities, significantly reduced the amount of code required to develop the Holoscan for Media based application. Using DeepStream components for real-time video processing and NMOS (Networked Media Open Specifications) signaling, we were able to keep our focus on the CABR technology and video processing.

The NVIDIA DeepStream SDK provides an excellent framework for developers to build and customize dynamic video processing pipelines. DeepStream provides pipeline components that make it very simple to build and deploy live video processing pipelines that utilize the hardware decoders and encoders available on all NVIDIA GPUs.

Beamr CABR dynamically adjusts video bitrate in real-time, optimizing quality and bandwidth use. It reduces data transmission without compromising video quality, making the video streaming more efficient. Recently we released our GPU implementation which uses the NVIDIA NVENC, encoder, providing significantly higher performance compared to previous solutions.

Taking our GPU implementation for CABR to the next level, we have built a GStreamer Plugin. With our GStreamer Plugin, users can now easily and seamlessly incorporate the CABR solution into their existing DeepStream pipelines as a simple drop-in replacement to their current encoder component.

Holoscan For Media


A GStreamer Pipeline Example

To illustrate the simplicity of using CABR, consider a simple DeepStream transcoding pipeline that reads and writes from files.


Simple DeepStream Pipeline: 
gst-launch-1.0 -v \
  filesrc location="video.mp4" ! decodebin ! nvvideoconvert ! queue \
  nvv4l2av1enc bitrate=4500 ! mp4mux ! filesink location="output.mp4"

By simply replacing the nvv4l2av1enc component with our CABR component, the encoding bitrate is adapted in real-time, according to the content, ensuring optimal bitrate usage for each frame, without any loss of perceptual quality.


CABR-Enhanced DeepStream Pipeline:
gst-launch-1.0 -v \
  filesrc location="video.mp4" ! decodebin ! nvvideoconvert ! queue \
  beamrcabvav1 bitrate=4500 ! mp4mux ! filesink location="output_cabr.mp4"


Similarly, we can replace the encoder component used in a live streaming pipeline with the CABR component to optimize live video streams, dynamically adjusting the output bitrate and offering up to a 50% reduction in data usage without sacrificing video quality.


Simple DeepStream Pipeline:
gst-launch-1.0 -v \
  rtmpsrc location=rtmp://someurl live=1 ! decodebin ! queue ! \ 
  nvvideoconvert ! queue ! nvv4l2av1enc bitrate=3500 ! \
  av1parse ! rtpav1pay mtu=1300 ! srtsink uri=srt://:8888

CABR-Enhanced DeepStream Pipeline:
gst-launch-1.0 -v \
  rtmpsrc location=rtmp://someurl live=1 ! decodebin ! queue ! \
  nvvideoconvert ! queue ! beamrcabrav1 bitrate=3500 ! \
  av1parse ! rtpav1pay mtu=1300 ! srtsink uri=srt://:8888


The Broad Horizons of CABR Integration in Live Media

Beamr CABR, demonstrated using NVIDIA Holoscan for Media at NAB show, marks just the beginning. This technology is an ideal fit for applications running on NVIDIA RTX GPU-powered accelerated computing and sets a new standard for video encoding.

Lowering the video bitrate reduces the required bandwidth when ingesting video to the cloud, creating new possibilities where high resolution or quality were previously costly or not even possible. Similarly, reduced bitrate when encoding on the cloud allows for streaming of higher quality videos at lower cost.

From file-based encoding to streaming services — the potential use cases are diverse, and the integration has never before been so simple. Together, let’s step into the future of media
streaming, where quality and efficiency coexist without compromise.

Uncategorized

Beamr teams with NVIDIA to accelerate Beamr technology on NVIDIA GPUs

Posted on by Tamar Shoham

2023 is a very exciting year for Beamr. In February Beamr became a public company on NASDAQ:BMR on the premise of making our video optimization technology globally available as a SaaS. This month we are already announcing a second milestone for 2023: Release of the Nvidia driver that enables running our technology on the Nvidia platform. This is a result of a 2 year joint project, where Beamr engineers worked alongside the amazing engineering team at Nvidia to ensure that the Beamr solution can be integrated with all Nvidia codecs – AVC, HEVC and AV1. 

The new NVENC driver, just now made public, provides an API that allows external control over NVENC, enabling Nvidia partners such as Beamr to tightly integrate with the NVENC H/W encoders for AVC, HEVC and AV1. Beamr is excited to have been a design partner for development of this API and to be the first company that uses it, to accelerate and reduce costs of video optimization. 

This milestone with Nvidia offers some important benefits. A significant cost reduction is achieved when performing Beamr video optimization using this platform. For example, for 4Kp60 encoded with advanced codecs, when using the Beamr video optimization on GPU the costs of video optimization can be cut by a factor of x10, compared to running on CPU. 

Using the Beamr solution integrated on GPU means that the encoding can be performed using the built in H/W codecs, which offer very fast, high frame rate, encoding. This means the combined solution can support live and real time video encoding which is a new use case for the Beamr video optimization technology.

In addition, Nvidia recently announced their AV1 codec, considered to be the highest quality AV1 HW accelerated encoder. In this comparison Jarred Walton concluded that “”From an overall quality and performance perspective, Nvidia’s latest Ada Lovelace NVENC hardware comes out as the winner with AV1 as the codec of choice”. When using the new driver to combine the Beamr video optimization with this excellent AV1 implementation, a very competitive solution is obtained, with video encoding abilities exceeding other AV1 encoders on the market.

So, how does the new driver actually allow the integration of NVENC codecs with Beamr video optimization technology? 

Above you can see a high level illustration of the system flow. The user video is ingested, and for each video frame the encoding parameters are controlled by the Beamr Quality Control block instructing NVENC on how to encode the frame, to reach the target quality while minimizing bit consumption. The New NVENC API layer is what enables the interactions between the Beamr Quality Control and the encoder to create the reduced bitrate, target optimized video. As part of the efforts towards the integrated solution, Beamr also ported its quality measurement IP to GPU and redesigned it to match the performance of NVENC, thus placing the entire solution on the GPU.

Beamr uses the new API to control the encoder and perform optimization which can reduce bitrate of an input video, or of a target encode, while guaranteeing the perceptual quality is preserved, thus creating encodes with the same perceptual quality at lower bitrates or file sizes.

The Beamr optimization may also be used for automatic, quality guaranteed codec modernization, where input content can be converted to a modern codec such as AV1, while guaranteeing each frame of the optimized encode is perceptually identical to the source video. This allows for faster migration to modern codecs, for example from AVC to HEVC or AVC to AV1, in an automated, always safe process – with no loss of quality.

In the below examples the risk of blind codec modernization is clearly visible, showcasing the advantage of using Beamr technology for this task. In these examples, we took AVC sources and encoded them to HEVC, to benefit from the increased compression efficiency offered by the more advanced coding standard. On the test set we used, Beamr reduced the source clips by 50% when converting to perceptually identical HEVC streams. We compare these encodes to the results obtained when performing ‘brute force’ compression to HEVC, using 50% lower bitrates. As is clear in these examples, using the blind conversion, shown on the left, can introduce disturbing artifacts compared to the source, shown in the middle. The Beamr encodes however, shown on the right, preserve the quality perfectly.

This driver release and the technology enablement it offers, while a significant milestone, is just the beginning. Beamr is now building a new SaaS that will allow a scalable, no code, implementation of its technology for reducing storage and networking costs. This service is planned to be publicly available in Q3 of 2023. In addition Beamr is looking for design partners that will get early access to its service and help us build the best experiences for our customers. 

At the same time Beamr will continue to strengthen relationships with existing users by offering them low level API’s for enhanced controls and specific workflow adaptations. 

For more information please contact us at info@beamr.com