Towards Stereoscopic Video Deblurring Using Deep Convolutional Networks

EasyChair Preprint 6911

Abstract

These days stereoscopic cameras are commonly used in daily life, such as the new smartphones and emerging technologies. The quality of the stereo video can be affected by various factors (e.g., blur artifact due to camera/object motion). For solving this issue, several methods are proposed for monocular deblurring, and there are some limited proposed works for stereo content deblurring. This paper presents a novel stereoscopic video deblurring model considering the consecutive left and right video frames. To compensate for the motion in stereoscopic video, we feed consecutive frames from the previous and next frames to the 3D CNN networks, which can help for further deblurring. Also, our proposed model uses the stereoscopic other view information to help for deblurring. Specifically, to deblur the stereo frames, our model takes left and right stereoscopic frames and some neighboring left and right frames as the inputs. Then, 3D Convolutional Neural Network (CNN) is applied to the left and right batches of frames to extract their features. This model consists of the modified 3D U-Net networks. To aggregate the left and right features, the Parallax Attention Module (PAM) is modified to fuse the left and right features and create the output deblurred frames. The experimental results on the recently proposed Stereo Blur dataset show that the proposed method can effectively deblur the blurry stereoscopic videos.

Keyphrases: Convolutional Neural Networks, Disparity, PAM, image deblurring, motion, stereoscopic video

@booklet{EasyChair:6911,
  author    = {Hassan Imani and Md Baharul Islam},
  title     = {Towards Stereoscopic Video Deblurring Using Deep Convolutional Networks},
  howpublished = {EasyChair Preprint 6911},
  year      = {EasyChair, 2021}}