Video Reflection Removal by Modified EDVR and 3D Convolution

Sota MORIYAMA; Koichi ICHIGE; Yuichi HORI; Masayuki TACHI

doi:10.1587/transfun.2023EAL2078

Regular Section

Video Reflection Removal by Modified EDVR and 3D Convolution

Sota MORIYAMA, Koichi ICHIGE, Yuichi HORI, Masayuki TACHI

著者情報

キーワード: video reflection removal, video restoration, machine learning, convolutional neural network, deformable convolutions, 3D convolutions

ジャーナルフリー

2024 年 E107.A 巻 8 号 p. 1430-1434

DOI https://doi.org/10.1587/transfun.2023EAL2078

Browse “Advance online publication” version

詳細

抄録

In this paper, we propose a method for video reflection removal using a video restoration framework with enhanced deformable networks (EDVR). We examine the effect of each module in EDVR on video reflection removal and modify the models using 3D convolutions. The performance of each modified model is evaluated in terms of the RMSE between the structural similarity (SSIM) and the smoothed SSIM representing temporal consistency.

責任著者(Corresponding author)

J-STAGEへの登録はこちら（無料）