Video Enhancement - Smart Tone Mapping
See the difference Smart Tone Mapping can make
Click the orange play button to see how Smart Tone Mapping converts HDR video to SDR video with Visionular's Video Enhancement feature, Smart Tone Mapping.
More about Video Enhancement
The process of encoding video involves more than just the encoding. Analyzing and preparing your source content is equally important. Visionular has developed a suite of AI-driven image enhancement processes that can intelligently apply the correct optimization before the encoder goes to work. Perhaps most importantly, our AI communicates with the encoder, so it knows how to encode each video considering the pre-encode optimizations.
Smart Tone Mapping
Some devices are unable to decode and display HDR video with high dynamic ranges properly. This is where Smart Tone Mapping comes in handy, intelligently converting HDR video to SDR while maintaining as much dynamic range as possible. You’re free of many of the bitrate and device restrictions.
Since SDR devices don’t have as great a dynamic range as the HDR images they display, you need a non-linear tone mapping algorithm. Although there are algorithms that can show HDR images and videos on all types of monitors, every display is different, which causes viewer experiences to be dissimilar.
To solve this, we carry out numerous tone mapping experiments to specify certain colors in the RGB space for uniform sampling while also encoding our video in the REC.709 space.
To find the closest color in BT.2020 space, we use a spectrophotometer. From there, we take those two data points to generate a high-accuracy tone-mapping algorithm which is used as an adaptive tone-mapping model.
Behind The Curtain
HDR to SDR with Smart Tone Mapping
Because the brightness range of SDR display devices is much smaller than that of HDR images, and with the brightness range seen in nature including the relationship between the human eye’s perception of brightness and brightness intensity as perceived by the human eye, non-linear processing is required when designing tone mapping algorithms. Tone mapping algorithms use different processing methods, but the traditional tone mapping methods can be described by the following formulas:
Where ‘f’ represents the tone mapping operator, ‘I’ represents the image to be operated, ‘w’ and ‘h’ represent the width and height of the image, and ‘c’ represents the number of channels of the image, usually, this is RGB, meaning three channels are the most common.
Here ‘C’ and ‘c’ are the colors before and after tone mapping, respectively. ‘L’ represents the brightness of the HDR image, while ‘T’ is the corresponding brightness value after tone mapping. ‘s’ is the parameter used to adjust saturation provided s<1.
Visionular has a lot of respect for the work that goes into making films. We want to make sure that every video, no matter when it was made or what equipment it was made on, can be viewed and enjoyed to its fullest extent. While we are proud of our technology, we are always looking for ways to improve it so that every Director’s and DP’s artistic vision can be preserved for future generations.
We train the generative adversarial networks using millions of high-definition images and video sets with extended datasets. These training datasets cover a variety of content types and resolutions, which meet the super-score requirements of a multitude of scenarios.
Customer Use Case
Xiaohongshu, which is also known as
Little Red Book, is a social media and
e-commerce platform. China’s answer
to Instagram, Xiaohongshu, had over
300 million registered users in 2019,
with 85 million monthly active users.
Many social media sites are blamed for lowering the quality of their uploaded material. Red Book wanted to set itself apart by addressing this problem.
They achieved higher-quality video with even lower bitrates after adopting Visionular’s Aurora Encoder and implementing smart tone mapping. In addition, they cut their operational expenses as a result of the savings in storage and bandwidth. They also reported increased platform viewership engagement thanks to the better quality video available on their network, resulting in increased revenue.