.png){kind=icon}
返回
Multi-exposure high dynamic range imaging based on LSGAN
.png){kind=icon}
PRE
AI
DOI：10.1016/j.displa.2024.102707.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep learning-based multi-exposure HDR imaging methods achieve better performance than traditional methods in recovering image information and removing ghosting artifacts, but still produce images with severe ghosting artifacts when dealing with poorly exposed dynamic scenes. In this paper, we proposed a least square generative adversarial network (LSGAN) based HDR imaging algorithm for dynamic scenes. In the generator, we presented a global dilated residual dense block (GDRDB) as the basic component for feature fusion. The GDRDB is able to acquire both local and global information of the images, so that the network can both preserve image details and remove ghosting artifacts effectively. We use two stages to train the model. The first phase pre-trains the generator network by content loss, and the second phase adversarially trains the generators and discriminators by LSGAN loss. Extensive experiments on three benchmark datasets show that our approach outperforms most of state-of-the-art methods qualitatively and quantitatively.
Keyword:
High dynamic imaging
Multi-exposure imaging
LSGAN
Deghosting
期刊
IF:
3.4
论文数:
2.3K
被引数:
3.2K
机构
暂无机构信息
引用论文
Research on Monitoring the Transmission Line Tension and Galloping Based on FBG Fitting Sensor基于FBG拟合传感器的输电线路张力及舞动监测研究
.png){kind=icon}
PREAI
分享收藏The real-world efficacy and safety of anlotinib in advanced non-small cell lung cancer安罗替尼在晚期非小细胞肺癌中的真实世界有效性与安全性
OAAI
OAAI分享收藏Characteristic fruit wine production via reciprocal selection of juice and non-Saccharomyces species
PREAI
分享收藏
查看更多内容