DeepFlash: Turning a flash selfie into a studio portrait

作者：

Highlights：

• A pipeline to turn a smartphone flash selfie into a studio portrait is provided.

• Pipeline consists of the following steps:-  Data collection by well-defined acquisition parameters;-  Pre-processing by the bilateral filter;-  Training the network;-  Validating the results;-  Comparisons of results with other similar approaches.

摘要

•A pipeline to turn a smartphone flash selfie into a studio portrait is provided.•Pipeline consists of the following steps:-  Data collection by well-defined acquisition parameters;-  Pre-processing by the bilateral filter;-  Training the network;-  Validating the results;-  Comparisons of results with other similar approaches.

论文关键词：Image enhancement,Machine learning algorithms,Deep learning,Computational photography,Image processing

论文评审过程：Received 12 January 2019, Revised 16 April 2019, Accepted 27 May 2019, Available online 30 May 2019, Version of Record 4 June 2019.

论文官网地址：https://doi.org/10.1016/j.image.2019.05.013