Deep Hierarchical Video Compression
DOI:
https://doi.org/10.1609/aaai.v38i8.28733Keywords:
DMKM: Data Compression, DMKM: Mining of Spatial, Temporal or Spatio-Temporal DataAbstract
Recently, probabilistic predictive coding that directly models the conditional distribution of latent features across successive frames for temporal redundancy removal has yielded promising results. Existing methods using a single-scale Variational AutoEncoder (VAE) must devise complex networks for conditional probability estimation in latent space, neglecting multiscale characteristics of video frames. Instead, this work proposes hierarchical probabilistic predictive coding, for which hierarchal VAEs are carefully designed to characterize multiscale latent features as a family of flexible priors and posteriors to predict the probabilities of future frames. Under such a hierarchical structure, lightweight networks are sufficient for prediction. The proposed method outperforms representative learned video compression models on common testing videos and demonstrates computational friendliness with much less memory footprint and faster encoding/decoding. Extensive experiments on adaptation to temporal patterns also indicate the better generalization of our hierarchical predictive mechanism. Furthermore, our solution is the first to enable progressive decoding that is favored in networked video applications with packet loss.Downloads
Published
2024-03-24
How to Cite
Lu, M., Duan, Z., Zhu, F., & Ma, Z. (2024). Deep Hierarchical Video Compression. Proceedings of the AAAI Conference on Artificial Intelligence, 38(8), 8859-8867. https://doi.org/10.1609/aaai.v38i8.28733
Issue
Section
AAAI Technical Track on Data Mining & Knowledge Management