Cross-View Integration for Stereoscopic Video Deblurring

Stereoscopic cameras are now often seen in modern technology, including new Cellphones. Numerous elements, such as blur artifacts from camera/object motion, might influence the stereo video's quality. There are various deblurring techniques for monocular content, yet there are not many works for stereo content. A novel encoder-decoder-based stereoscopic video deblurring model presented in this work considers the subsequent left and right video frames. This approach employs the cross-view stereoscopic information to aid in deblurring. The proposed model uses the left and right stereoscopic frames and some nearby left and right frames as inputs to deblur the middle stereo frames. To extract their features, we first apply the stereo batch of frames to the encoder of our model. The left and right features are then fused together after being aggregated using the Parallax Attention Module (PAM). The decoder then extracts the deblurred stereo video frames using the output of PAM features. According to experimental findings on the recently proposed Stereo Blur dataset, the proposed approach effectively deblurs the stereoscopic video frames.