all AI news
Perceptual Quality Assessment of Face Video Compression: A Benchmark and An Effective Method. (arXiv:2304.07056v1 [eess.IV])
cs.LG updates on arXiv.org arxiv.org
Recent years have witnessed an exponential increase in the demand for face
video compression, and the success of artificial intelligence has expanded the
boundaries beyond traditional hybrid video coding. Generative coding approaches
have been identified as promising alternatives with reasonable perceptual
rate-distortion trade-offs, leveraging the statistical priors of face videos.
However, the great diversity of distortion types in spatial and temporal
domains, ranging from the traditional hybrid coding frameworks to generative
models, present grand challenges in compressed face video quality …
artificial artificial intelligence arxiv benchmark beyond challenges coding compression demand diversity face frameworks generative generative models hybrid intelligence paper quality rate statistical success temporal trade types video video compression videos