Preliminary Study on Video Codec Optimization Using VMAF
Abstract: The growth in video streaming has been an exponential one for the last decade or so. High-resolution videos require high bandwidth to transport the videos over the network. There has been a growing demand for compression technologies to compress videos while simultaneously maintaining quality. Video codecs are used to encode and decode video streams. These codecs have been developed by MPEG, Google, Microsoft, and Apple Inc. There are many encoding parameters that affect bitrate and video quality. These performance parameters must be exploited, evaluated, and modeled to find the best possible solutions. This paper demonstrates some preliminary results for video coding sets with selected bitrates. The objective video multimethod assessment fusion (VMAF) metric is calculated for the encoded video versions. In this study, the quality of the encoded videos was evaluated and estimated using VMAF. The results confirm a strong relationship between bitrate and VMAF estimates. This study shows the impact of coding parameters on the VMAF values and provides the foundation for building robust models in the field of video quality analysis.
Loading