Adversarial Distortion for Learned Video Compression

Veerabadran, Vijay; Pourreza, Reza; Habibian, Amirhossein; Cohen, Taco

doi:10.1109/cvprw50498.2020.00092

Cited by 7 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then they employ two auto-encoder networks to compress the corresponding motion and residual information. Veerabadran et al [2020] show that minimizing an auxiliary adversarial distortion objective for neural video compression in the low bitrate setting creates distortions that better correlate with human perception. Djelouah et al [2019b] propose compressing and sending residuals in the latent space instead of residuals in the pixel space, which allows the reuse of the same image compression network for both keyframes and intermediate frames.…”

Section: Neural Video Compressionmentioning

confidence: 97%

Microdosing: Knowledge Distillation for GAN based Compression

Helminger¹,

Azevedo²,

Djelouah³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recently, significant progress has been made in learned image and video compression. In particular, the usage of Generative Adversarial Networks has led to impressive results in the low bit rate regime. However, the model size remains an important issue in current state-of-the-art proposals, and existing solutions require significant computation effort on the decoding side. This limits their usage in realistic scenarios and the extension to video compression. In this paper, we demonstrate how to leverage knowledge distillation to obtain equally capable image decoders at a fraction of the original number of parameters. We investigate several aspects of our solution including sequence specialization with side information for image coding. Finally, we also show how to transfer the obtained benefits into the setting of video compression. Altogether, our proposal allows to reduce a decoder model size by a factor of 20 and to achieve 50% reduction in decoding time.Preprint. Under review.

show abstract

Section: Neural Video Compressionmentioning

confidence: 97%

Microdosing: Knowledge Distillation for GAN based Compression

Helminger¹,

Azevedo²,

Djelouah³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Video coding VAE DeepCoder [130] Feature prediction VCIP 2017 LVC [131] Predictive coding TCSVT 2019 LVR [132] LSTM predictor ICML 2015 RDAVC [133] R-D Autoencoder ICCV 2019 DGVC [134] Local & global feature NIPS 2019 CSRVC [135] Spatiotemporal RNN TCSVT 2021 HMC [136] Compound spatiotemporal representation TCSVT 2022 GAN ADLVC [137] Feature prediction CVPRW 2020 LSVC [135] ConvLSTM CVPR 2021 NTHSVC [138] 3D keypoint extractor CVPR 2021 DHBC [139] Contrastive learning ICME 2022…”

Section: Learning-based Codingmentioning

confidence: 99%

Overview of intelligent video coding: from model-based to learning-based approaches

Gao

Wang

et al. 2023

Vis. Intell.

View full text Add to dashboard Cite

Intelligent video coding (IVC), which dates back to the late 1980s with the concept of encoding videos with knowledge and semantics, includes visual content compact representation models and methods enabling structural, detailed descriptions of visual information at different granularity levels (i.e., block, mesh, region, and object) and in different areas. It aims to support and facilitate a wide range of applications, such as visual media coding, content broadcasting, and ubiquitous multimedia computing. We present a high-level overview of the IVC technology from model-based coding (MBC) to learning-based coding (LBC). MBC mainly adopts a manually designed coding scheme to explicitly decompose videos to be coded into blocks or semantic components. Thanks to emerging deep learning technologies such as neural networks and generative models, LBC has become a rising topic in the coding area. In this paper, we first review the classical MBC approaches, followed by the LBC approaches for image and video data. We also discuss and overview our recent attempts at neural coding approaches, which are inspiring for both academic research and industrial implementation. Some critical yet less studied issues are discussed at the end of this paper.

show abstract

High-resolution image compression algorithms in remote sensing imaging

2023

Displays

View full text Add to dashboard Cite

Adversarial Distortion for Learned Video Compression

Cited by 7 publications

References 16 publications

Microdosing: Knowledge Distillation for GAN based Compression

Microdosing: Knowledge Distillation for GAN based Compression

Overview of intelligent video coding: from model-based to learning-based approaches

High-resolution image compression algorithms in remote sensing imaging

Contact Info

Product

Resources

About