ANFIC: Image Compression Using Augmented Normalizing Flows

Ho, Yung-Han; Chan, Chih-Chun; Peng, Wen-Hsiao; Hang, Hsueh-Ming; Domański, Marek

doi:10.1109/ojcas.2021.3123201

Cited by 35 publications

(30 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Henter, Gustav Eje et al [57] proposed a model for probability, generation, and controllable motion data based on normalizing flows with MoGlow. The model is used to generate motion data sequences from normalizing flows so that it cannot only describe the distribution with high complexity but can use accurate maximum likelihood for effective training; Ho, YH et al [58] built an end-to-end learning image compression system based on a novel flow model Augmented Normalizing Flows (ANF) and stacked with multiple Variational Auto-encoders (VAEs) is built.…”

Section: Related Workmentioning

confidence: 99%

PFVAE: A Planar Flow-Based Variational Auto-Encoder Prediction Model for Time Series Data

et al. 2022

View full text Add to dashboard Cite

Prediction based on time series has a wide range of applications. Due to the complex nonlinear and random distribution of time series data, the performance of learning prediction models can be reduced by the modeling bias or overfitting. This paper proposes a novel planar flow-based variational auto-encoder prediction model (PFVAE), which uses the long- and short-term memory network (LSTM) as the auto-encoder and designs the variational auto-encoder (VAE) as a time series data predictor to overcome the noise effects. In addition, the internal structure of VAE is transformed using planar flow, which enables it to learn and fit the nonlinearity of time series data and improve the dynamic adaptability of the network. The prediction experiments verify that the proposed model is superior to other models regarding prediction accuracy and proves it is effective for predicting time series data.

show abstract

Section: Related Workmentioning

confidence: 99%

PFVAE: A Planar Flow-Based Variational Auto-Encoder Prediction Model for Time Series Data

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Architecture: Motivated by [13], our conditional inter-frame coder is a hybrid of the two-step and the hierarchical ANF's. The two autoencoding transforms {g enc π1 , g dec π1 }, {g enc π2 , g dec π2 } convert x t , e z into their latents y 2 , z 2 , respectively, while the hierarchical autoencoding transform {h enc π3 , h dec π3 } acts as the hyperprior codec, encoding the latent z 2 into the hyperprior representation ĥ2 .…”

Section: Canf-based Inter-frame Codermentioning

confidence: 99%

“…Many follow-up works have been centered around enhancing the autoencoder network [9,8] and/or improving the prior modeling [30,9]. Lately, there have been few attempts at introducing normalizing flow models [28,13] to learned image compression Inspired by the success of learned image compression, research on learned video compression is catching up quickly. However, most end-to-end learned video compression systems [26,27,24,14,32] were developed based primarily on the traditional, hybrid-based coding architecture, replacing key components, such as inter-frame prediction and residual coding, with neural networks.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…In this paper, we present a conditional augmented normalizing flow-based video compression (CANF-VC) system, which is inspired partly by the ANFbased image compression (ANFIC) [13]. However, while ANFIC [13] adopts ANF to learn the (unconditional) image distribution p(x) for image compression, we address video compression from the perspective of learning a video generative model by maximizing the conditional likelihood p(x t |x c ). We choose the conditional augmented normalizing flow (CANF) to learn p(x t |x c ), because ANF is a special type of generative model, which includes VAE as a special case and is able to achieve superior expressiveness to VAE.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

CANF-VC: Conditional Augmented Normalizing Flows for Video Compression

Ho¹,

Chang²,

Chen³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

This paper presents an end-to-end learning-based video compression system, termed CANF-VC, based on conditional augmented normalizing flows (CANF). Most learned video compression systems adopt the same hybrid-based coding architecture as the traditional codecs. Recent research on conditional coding has shown the sub-optimality of the hybrid-based coding and opens up opportunities for deep generative models to take a key role in creating new coding frameworks. CANF-VC represents a new attempt that leverages the conditional ANF to learn a video generative model for conditional inter-frame coding. We choose ANF because it is a special type of generative model, which includes variational autoencoder as a special case and is able to achieve better expressiveness. CANF-VC also extends the idea of conditional coding to motion coding, forming a purely conditional coding framework. Extensive experimental results on commonly used datasets confirm the superiority of CANF-VC to the state-of-the-art methods. The source code of CANF-VC is available at https://github.com/NYCU-MAPL/CANF-VC.

show abstract

CANF-VC: Conditional Augmented Normalizing Flows for Video Compression

Chang

Chen

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

ANFIC: Image Compression Using Augmented Normalizing Flows

Cited by 35 publications

References 11 publications

PFVAE: A Planar Flow-Based Variational Auto-Encoder Prediction Model for Time Series Data

PFVAE: A Planar Flow-Based Variational Auto-Encoder Prediction Model for Time Series Data

CANF-VC: Conditional Augmented Normalizing Flows for Video Compression

CANF-VC: Conditional Augmented Normalizing Flows for Video Compression

Contact Info

Product

Resources

About