CVPR2020
Learning to See Through Obstructions
Yu-Lun Liu, Wei-Sheng Lai, Ming-Hsuan Yang, Yung-Yu Chuang, Jia-Bin Huang
Abstract
https://www.cmlab.csie.ntu.edu.tw/ ˜yulunliu/ObstructionRemoval (a) Reflection removal (b) Fence removal (c) Raindrop removal Figure 1: Seeing through obstructions. We present a learning-based method for recovering clean images from a given short sequence of images taken by a moving camera through obstructing elements such as (a) windows, (b) fence, or (c) raindrop.