Skip to main content

Per-Scene Encoding in Test

· One min read
Grigory Grin
Grigory Grin
Chief Developer Advocate

Per-scene encoding or CAE (Content-Aware Encoding) is a technique used to optimize the size of the encoded output by applying different encoder settings to different parts of the video (scenes). An AI-enhanced solution continuously analyzes content in real-time to determine the best transcoder settings for outstanding video quality and lower bitrates. It's also known as CAE - Content-Aware Encoding or Content-Adaptive Encoding.

Per-scene encoding promises to reduce the output size by an average of 40% (and up to 70%) without compromising visual video quality. But how well it works really?

In this article, we tested per-scene encoding by applying optimization to the reference video with various options (various target VMAF scores) and compared the results. You will find:

  • Visual quality comparison using an embedded side-by-side player showing the videos with and without per-scene encoding
  • Computed VMAF scores for each frame
  • Cost calculation and comparison

For details, read the full article.

If you don't have time to read the article, our recommendation is: do apply per-scene encoding to save on delivery costs, and for optimal balance between the size and the quality use a target VMAF score of 98.