Portal de Periódicos da CAPES

RCBSR: Re-parameterization Convolution Block for Super-Resolution

2023; Springer Science+Business Media; Linguagem: Inglês

10.1007/978-3-031-25063-7_33

1611-3349

Si Gao, Chengjian Zheng, Xiaofeng Zhang, Shaoli Liu, Biao Wu, Kaidi Lu, Diankai Zhang, Ning Wang,

Advanced Vision and Imaging

Super resolution(SR) with high efficiency and low power consumption is highly demanded in the actual application scenes. In this paper, We designed a super light-weight SR network with strong feature expression. The network we proposed is named RCBSR. Based on the novel technique of re-parameterization, we adopt a block with multiple paths structure in the training stage and merge multiple paths structure into one single 3 $$\times $$ 3 convolution in the inference stage. And then the neural architecture search(NAS) method is adopted to determine amounts of block M and amounts of channel C. Finally, the proposed SR network achieves a fairly good result of PSNR(27.52 dB) with power consumption(0.1 W@30 fps) on the MediaTek Dimensity 9000 platform in the challenge testing stage.