A 0.76 mm<sup>2</sup> 0.22 nJ/Pixel DL-Assisted 4K Video Encoder LSI for Quality-of-Experience Over Smartphones

Liu, Tsu-Ming; Tsai, Chang-Hung; Wu, Tongsuo; Lin, Jiusheng; Chen, Liheng; Chou, Han-Liang; Chang, Yung-Chang; Chen, Ju

doi:10.1109/lssc.2019.2905958

Cited by 8 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A deep learning approach to reduction of HEVC encoding complexity by Liu et al [90] shows the lowest power consumption of all the reviewed HEVC/AVC ASIC encoders. Deep learning tools have been also used [85,107] to reduce the inter and intra prediction complexity of VVC, respectively.…”

Section: Discussionmentioning

confidence: 99%

“…Liu et al [90] proposed a ASIC implementation of a deep learningśassisted HEVC encoder capable of 4K encoding at 30 FPS. A neural network is trained to recognize the human visual contact ield to estimate the visual attention distribution which is then used to guide the selection of encoding parameters.…”

Section: Inter-frame Compressionmentioning

confidence: 99%

“…Deep learning has been used to accelerate complex steps of existing algorithms [85,90,107,115]. While the computational cost of deep learning inference is very high, it might still be lower than some parts of modern complex formats such as ASTC or VVC.…”

Section: Future Prospectsmentioning

confidence: 99%

See 2 more Smart Citations

Image and Video Coding Techniques for Ultra-low Latency

et al. 2022

View full text Add to dashboard Cite

The next generation of wireless networks fosters the adoption of latency-critical applications such as XR, connected industry, or autonomous driving. This survey gathers implementation aspects of different image and video coding schemes and discusses their tradeoffs. Standardized video coding technologies such as HEVC or VVC provide a high compression ratio, but their enormous complexity sets the scene for alternative approaches like still image, mezzanine, or texture compression in scenarios with tight resource or latency constraints. Regardless of the coding scheme, we found inter-device memory transfers and the lack of sub-frame coding as limitations of current full-system and software-programmable implementations.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Inter-frame Compressionmentioning

confidence: 99%

See 1 more Smart Citation

Image and Video Coding Techniques for Ultra-low Latency

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Deep neural networks have made rapid advances on diverse multimedia tasks [6,28,33], especially the image transformation problems including denoising [9], super-resolution [24], frame interpolation [29], and so on. Specifically speaking, a generative network is learned to reconstruct high-quality output images from degraded input image under a supervised manner.…”

Section: Introductionmentioning

confidence: 99%

Perceptually Optimizing Deep Image Compression

Chen,

Bampis,

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Mean squared error (MSE) and ℓ p norms have largely dominated the measurement of loss in neural networks due to their simplicity and analytical properties. However, when used to assess visual information loss, these simple norms are not highly consistent with human perception. Here, we propose a different proxy approach to optimize image analysis networks against quantitative perceptual models. Specifically, we construct a proxy network, which mimics the perceptual model while serving as a loss layer of the network. We experimentally demonstrate how this optimization framework can be applied to train an end-to-end optimized image compression network. By building on top of a modern deep image compression models, we are able to demonstrate an averaged bitrate reduction of 28.7% over MSE optimization, given a specified perceptual quality (VMAF) level.

show abstract

A fast integrated deblocking filter and sample-adaptive-offset parameter estimation architecture for HEVC

Singhadia

Minhazuddin

Mamillapalli

et al. 2021

Microprocessors and Microsystems

View full text Add to dashboard Cite

A 0.76 mm² 0.22 nJ/Pixel DL-Assisted 4K Video Encoder LSI for Quality-of-Experience Over Smartphones

Cited by 8 publications

References 7 publications

Image and Video Coding Techniques for Ultra-low Latency

Image and Video Coding Techniques for Ultra-low Latency

Perceptually Optimizing Deep Image Compression

A fast integrated deblocking filter and sample-adaptive-offset parameter estimation architecture for HEVC

Contact Info

Product

Resources

About

A 0.76 mm2 0.22 nJ/Pixel DL-Assisted 4K Video Encoder LSI for Quality-of-Experience Over Smartphones

Cited by 8 publications

References 7 publications

Image and Video Coding Techniques for Ultra-low Latency

Image and Video Coding Techniques for Ultra-low Latency

Perceptually Optimizing Deep Image Compression

A fast integrated deblocking filter and sample-adaptive-offset parameter estimation architecture for HEVC

Contact Info

Product

Resources

About

A 0.76 mm² 0.22 nJ/Pixel DL-Assisted 4K Video Encoder LSI for Quality-of-Experience Over Smartphones