论文标题
BSRA：基于块的超级分辨率加速器，具有硬件有效像素的注意力
BSRA: Block-based Super Resolution Accelerator with Hardware Efficient Pixel Attention
论文作者
论文摘要
越来越多地，已经提出了基于卷积的神经网络（CNN）超级分辨率模型，以更好地重建结果，但是它们的较大模型大小和复杂的结构抑制了其实时硬件实施。当前的硬件设计仅限于普通网络，并且质量较低和内存带宽要求。本文提出了一个超级分辨率硬件加速器，具有硬件有效的像素注意力，仅需要25.9k参数和简单的结构，但比广泛使用的FSRCNN实现了0.38DB的重建图像。加速器采用完整的模型明智的卷积以进行完整的模型层融合，以减少外部内存访问模型输入和输出。另外，CNN和像素的注意力得到了具有分布重量的PE阵列的很好的支持。最终实现可以通过TSMC 40nm CMOS流程以每秒30帧的速度支持全高清图像重建。
Increasingly, convolution neural network (CNN) based super resolution models have been proposed for better reconstruction results, but their large model size and complicated structure inhibit their real-time hardware implementation. Current hardware designs are limited to a plain network and suffer from lower quality and high memory bandwidth requirements. This paper proposes a super resolution hardware accelerator with hardware efficient pixel attention that just needs 25.9K parameters and simple structure but achieves 0.38dB better reconstruction images than the widely used FSRCNN. The accelerator adopts full model block wise convolution for full model layer fusion to reduce external memory access to model input and output only. In addition, CNN and pixel attention are well supported by PE arrays with distributed weights. The final implementation can support full HD image reconstruction at 30 frames per second with TSMC 40nm CMOS process.
