Generalized Difference Coder: A Novel Conditional Autoencoder Structure for Video Compression
Motion compensated inter prediction is a common component of all video coders. The concept was established in traditional hybrid coding and successfully transferred to learning-based video compression. To compress the residual signal after prediction, usually the difference of the two signals is compressed using a standard autoencoder. However, information theory tells us that a general conditional coder is more efficient. In this paper, we provide a solid foundation based on information theory and Shannon entropy to show the potentials but also the limits of conditional coding. Building on those results, we then propose the generalized difference coder, a special case of a conditional coder designed to avoid limiting bottlenecks. With this coder, we are able to achieve average rate savings of 27.8% compared to a standard autoencoder, by only adding a moderate complexity overhead of less than 7%.
Code (0)
등록된 구현이 없습니다.
Tasks
Video CompressionSimilar Papers 제목 키워드 기반
Photorealistic Facial Expression Synthesis by the Conditional Difference Adversarial Autoencoder
Photorealistic facial expression synthesis from single face image can be widely applied to face recognition, data augmentation for emotion recognition or entertainment. This problem is challenging, in part due to a pauci…
Data AugmentationDecoderEmotion RecognitionFace RecognitionConditional Sampling via Wasserstein Autoencoders and Triangular Transport
We present Conditional Wasserstein Autoencoders (CWAEs), a framework for conditional simulation that exploits low-dimensional structure in both the conditioned and the conditioning variables. The key idea is to modify a …
Leveraging Variational Autoencoders for Parameterized MMSE Estimation
In this manuscript, we propose to use a variational autoencoder-based framework for parameterizing a conditional linear minimum mean squared error estimator. The variational autoencoder models the underlying unknown data…
Conditional Random Field Autoencoders for Unsupervised Structured Prediction
We introduce a framework for unsupervised learning of structured predictors with overlapping, global features. Each input's latent representation is predicted conditional on the observable data using a feature-rich condi…
MULTI-VIEW LEARNINGPredictionStructured PredictionWord AlignmentGeneralized Graph Transformer Variational Autoencoder
Graph link prediction has long been a central problem in graph representation learning in both network analysis and generative modeling. Recent progress in deep learning has introduced increasingly sophisticated architec…
Graph Representation LearningLink Prediction