Efficient Content-Driven Encoding Towards a Target Video Quality
Video streaming workflows aim to maximize video quality while still maintaining smooth video streaming performance. A traditional fixed bitrate ladder consists of predetermined bitrate-resolution pairs optimized across a wide variety of content. Consequently, these pairs are rarely optimized for a given piece of content. Some encoding tools address this by encoding each piece of video content with many codec parameters and then evaluating the results using a video quality metric. However, this process requires significant computation, which increases cost and encoding time. In this paper we propose a novel content-driven workflow that predicts optimal encoding parameters to achieve a target perceptual video quality. We do so by designing a deep learning model that, based on the video input, predicts a Video Multimethod Assessment Fusion (VMAF) rate-distortion curve. Our results indicate that such a content-driven approach efficiently reduces the number of encoding attempts, minimizes necessary cloud computing resources, encodes most efficiently, and maximizes perceptual video quality.
- Print ISSN
- 1545-0279
- Electronic ISSN
- 2160-2492
- Published
- 2025-01
- Content type
- Original Research
- Keywords
- bitrate ladder, live streaming, rate-quality curves, video coding, video compression
- DOI
- 10.5594/JMI.2025/JCRG7496