Year: 2024
Type: conference-paper
Abstract: 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.
Authors: Ming Lu, Zhihao Duan, Fengqing Zhu, Zhan Ma
Institutions: Nanjing University, Purdue University West Lafayette
Language: English
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
Award: G8505359809
OpenAlex ID: W4393148125