Kaihao Zhang, Wenhan Luo, Yiran Zhong, Lin Ma, Wei Liu...
TL;DR利用改进的 3D 卷积对空间和时间领域进行联合建模,进而提高视频去模糊性能,在 GAN 模型中使用内容和对抗损失函数对模型进行训练,并称其为 DBLRGAN 模型,测试结果最先进。
Abstract
Camera shake or target movement often leads to undesired blur effects in
videos captured by a hand-held camera. Despite significant efforts having been
devoted to video-deblur research, two major challenges remain: 1) how to model
the spatio-temporal characteristics across both the spatial domain (i.e., image
plane) and temporal domain (i.e., neighboring fra