Video Deblurring by Utilizing Non-local Reference Frames

MPhil Thesis Defence


Title: "Video Deblurring by Utilizing Non-local Reference Frames"

By

Mr. Zian QIAN


Abstract

In this thesis, we study the problem of video deblurring by utilizing nonlocal 
reference frames. Our key observation is that some frames in a video are much 
sharper than others, and thus we can transfer the texture information in these 
sharp reference frames to blurry frames. We first present an internal learning 
approach that heuristically selects sharp frames from a video and then trains a 
convolutional neural network on these sharp frames. The trained network often 
absorbs visual details in sharp reference frames to perform deblurring on all 
video frames. Such an internal learning approach can avoid the domain gap 
between synthetic training data and real-world test data, which is an issue for 
existing video deblurring approaches. While internal learning approaches are 
generally slow at test time, we also develop an external learning method with 
our proposed multi-head source reference attention module (MHSRA) to 
significantly reduce inference time for video deblurring with nonlocal 
reference frames. Our perceptual user study on real-world videos shows that our 
methods with nonlocal reference frames can reconstruct clearer and sharper 
videos than state-of-the-art video deblurring approaches.


Date:  			Thursday, 25 August 2022

Time:			2:30pm - 4:30pm

Zoom Meeting:		https://hkust.zoom.us/j/4789230621

Committee Members:	Dr. Qifeng Chen (Supervisor)
 			Dr. Dan Xu (Chairperson)
 			Dr. Hao Chen


**** ALL are Welcome ****