Overview of Research in the field of Video Compression using Deep Neural Networks

Birman, Raz; Hadar, Ofer

doi:10.1007/s11042-019-08572-3

Cited by 25 publications

(7 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the lossless compression ratio remains low (e.g., for RGB 24 bpp images it does not exceed 3.3 [ 15 ]). In ADAS/ADS applications, compression must be performed in real time by an on-board computer system with limited capacity, which precludes (at least currently) the use of complex compression algorithms, such as deep neural networks (DNN) [ 16 , 17 ].…”

Section: Lossless Compression For Adas and Adsmentioning

confidence: 99%

“…DNNs became a very popular solution for performing various classification, prediction, and identification tasks in images, including also image compression [ 16 , 33 ]. A recent overview of the research in the field of video compression using DNNs is presented in [ 17 ]. The authors of this survey point out two main directions of research in this area: improving existing video codecs by performing better predictions, and the elaboration of holistic methods for the end-to-end image or video compression schemes.…”

Section: State-of-the-art In the Lossless Compression Of Imagesmentioning

confidence: 99%

“…The authors of this survey point out two main directions of research in this area: improving existing video codecs by performing better predictions, and the elaboration of holistic methods for the end-to-end image or video compression schemes. They conclude that while some of the results are promising, no breakthrough has been reported so far [ 17 ]. It is worth noting here that the methods based on DNNs are still too complicated to operate in ADAS/ADS applications in real-time with the limited capacity of the on-board computing systems used.…”

Section: State-of-the-art In the Lossless Compression Of Imagesmentioning

confidence: 99%

See 2 more Smart Citations

Highly Efficient Lossless Coding for High Dynamic Range Red, Clear, Clear, Clear Image Sensors

Pawlowski

Piniarski

Dąbrowski

2021

Sensors

View full text Add to dashboard Cite

In this paper we present a highly efficient coding procedure, specially designed and dedicated to operate with high dynamic range (HDR) RCCC (red, clear, clear, clear) image sensors used mainly in advanced driver-assistance systems (ADAS) and autonomous driving systems (ADS). The coding procedure can be used for a lossless reduction of data volume under developing and testing of video processing algorithms, e.g., in software in-the-loop (SiL) or hardware in-the-loop (HiL) conditions. Therefore, it was designed to achieve both: the state-of-the-art compression ratios and real-time compression feasibility. In tests we utilized FFV1 lossless codec and proved efficiency of up to 81 fps (frames per second) for compression and 87 fps for decompression performed on a single Intel i7 CPU.

show abstract

Section: Lossless Compression For Adas and Adsmentioning

confidence: 99%

Section: State-of-the-art In the Lossless Compression Of Imagesmentioning

confidence: 99%

Section: State-of-the-art In the Lossless Compression Of Imagesmentioning

confidence: 99%

See 1 more Smart Citation

Highly Efficient Lossless Coding for High Dynamic Range Red, Clear, Clear, Clear Image Sensors

Pawlowski

Piniarski

Dąbrowski

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…However, further improvements are also needed towards the same pertaining to the limitations observed as specified. Birman et al (2020), illustrate and explain various issues for the video compression process in the field of DNNs. Still , additional investigation is looking to achieve the upcoming generation and neural networks-based codecs.…”

Section: Introductionmentioning

confidence: 99%

An Efficient Video Compression Framework using Deep Convolutional Neural Networks (DCNN)

Kumar¹,

Madhavi²,

Janaki³

2022

Journal of Computer Science

View full text Add to dashboard Cite

In the current world, video streaming has grown in popularity and now accounts for a large percentage of internet traffic, making it challenging for service providers to broadcast videos at high rates while utilizing less storage space. To follow inefficient analytical coding design, previous video compression prototypes require non-learning-based designs. As a result, we propose a DCNN technique that integrates OFE-Net, MVE-Net, MVD-Net, MC-Net, RE-Net, and RD-Net for getting an ideal collection of frames by linking each frame pixel with preceding and following frames, then finding linked blocks and minimizing un needed pixels. In terms of MS-SIM and PSNR, the proposed DCNN approach produces good video quality at low bit rates.

show abstract

“…overly large kernel size of the attention mechanism;(2) a discrepancy between train and test time behavior; (3) a large number of autoregressive steps. For an input image x ∈ R H×W ×3 with a latent representation ŷ ∈ R with height H, width W and the number of channels C), the complexity C of the Contextformer's attention mechanism expressed in number of MAC operations is:…”

mentioning

confidence: 99%

Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression

Koyuncu

Gao

Boev

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

In this work, we introduce Efficient Contextformer (eContextformer) for context modeling in lossy learned image compression, which is built upon our previous work, Contextformer. The eContextformer combines the recent advancements in efficient transformers and fast context models with the spatio-channel attention mechanism. The proposed model enables content-adaptive exploitation of the spatial and channelwise latent dependencies for a high performance and efficient entropy modeling. By incorporating several innovations, the eContextformer features improved decoding speed, model complexity and rate-distortion performance over previous work. For instance, compared to Contextformer, the eContextformer requires 145x less model complexity, 210x less decoding speed and achieves higher average bit savings on the Kodak, CLIC2020 and Tecnick datasets. Compared to the standard Versatile Video Coding (VVC) Test Model (VTM) 16.2, the proposed model provides up to 17.1% bitrate savings and surpasses various learning-based models.

show abstract

Overview of Research in the field of Video Compression using Deep Neural Networks

Cited by 25 publications

References 29 publications

Highly Efficient Lossless Coding for High Dynamic Range Red, Clear, Clear, Clear Image Sensors

Highly Efficient Lossless Coding for High Dynamic Range Red, Clear, Clear, Clear Image Sensors

An Efficient Video Compression Framework using Deep Convolutional Neural Networks (DCNN)

Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression

Contact Info

Product

Resources

About