Quality Assessment for Deep Learning-based Video Coding
Nükhet Özbek, Caner Mutlu · 2025
In this study, the H.265/HEVC video codec and the deep learning-based video codec called LHBDC (Learned Hierarchical Bi-Directional Video Compression) were compared on 1080p videos selectively encoded at certain values. During the comparison process, both objective metrics and subjective evaluations were used. By combining the results of objective metrics with the subjective perceptions of users, the advantages and disadvantages of the deep learning-based approach compared to the traditional method were analyzed. The findings showed that LHBDC has the potential to deliver higher quality, especially in high-motion scenes or low bit rates.