LiTMNet: A deep CNN for efficient HDR image reconstruction from a single LDR image

作者：

Highlights：

• We present a lightweight CNN for HDR image reconstruction from a single LDR image.

• Our approach is 38× faster than the state-of-the-art method on mobile devices.

• We demonstrate an android application for end-to-end HDR image reconstruction.

摘要

•We present a lightweight CNN for HDR image reconstruction from a single LDR image.•Our approach is 38× faster than the state-of-the-art method on mobile devices.•We demonstrate an android application for end-to-end HDR image reconstruction.

论文关键词：HDR image reconstruction,Lightweight CNN,Inverse tone mapping

论文评审过程：Received 29 April 2021, Revised 3 January 2022, Accepted 1 March 2022, Available online 6 March 2022, Version of Record 13 March 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108620