all AI news
Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compression. (arXiv:2207.05894v1 [eess.IV])
cs.CV updates on arXiv.org arxiv.org
For neural video codec, it is critical, yet challenging, to design an
efficient entropy model which can accurately predict the probability
distribution of the quantized latent representation. However, most existing
video codecs directly use the ready-made entropy model from image codec to
encode the residual or motion, and do not fully leverage the spatial-temporal
characteristics in video. To this end, this paper proposes a powerful entropy
model which efficiently captures both spatial and temporal dependencies. In
particular, we introduce the …
arxiv compression entropy hybrid modelling temporal video video compression