A 0.76MM2 0.22NJ/Pixel DL-Assisted 4K Video Encoder LSI for Quality-of-Experience Over Smart-Phones
| Autor: | Chi-cheng Ju, Chen Li-Heng, Chang-Hung Tsai, Han-Liang Chou, Tsu-Ming Liu, Tung-Hsing Wu, Jia-Ying Lin |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Channel (digital image)
Pixel Computer science business.industry Deep learning 02 engineering and technology Reduction (complexity) Encoding (memory) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Quality of experience Artificial intelligence business Encoder Computer hardware Efficient energy use |
| Zdroj: | VLSI Circuits |
| DOI: | 10.1109/vlsic.2018.8502304 |
| Popis: | This paper proposes the world's first deep learning (DL)-assisted video encoder LSI fabricated in a 10nm process with a core area of 0.76mm2 to integrate quad-core DL accelerators and 4K×2K H.264/H.265 video standards. A visual-contact-field network (VCFNet) DL model is newly designed to predict human focus information for extraordinary reducing the encoding complexity, leading to 82.3% of power reduction. Moreover, input channel reduction and layer merging approaches reduce VCFNet complexity by 69%. Operated at 0.9V and 504MHz, the proposed DL-assisted 4K video encoder LSI consumes 56.54mW to achieve 0.22nJ/pixel of energy efficiency, cutting 0.1-14nJ/pixel compared to conventional designs [1]–[3]. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|