CINE: A 4K-UHD Energy-Efficient Computational Imaging Neural Engine With Overlapped Stripe Inference and Structure-Sparse Kernel

Abstract

Recently, convolutional neural networks have achieved great success in high-resolution computational imaging (CI) applications, such as super-resolution, image denoising, and image style transfer. However, it demands an enormous number of external memory access, i.e., DRAM bandwidth, and intensive computation while inferencing deeper models for high-quality images. In this letter, an energy-efficient CI neural engine, CINE, is proposed with three key features: 1) overlapped stripe inference flow; 2) structure-sparse convolution kernel; and 3) weight-rotated allocation unit. As a result, CINE can provide 4.6-8.3 TOP/W of energy efficiency for high-quality CI applications.