Self-supervised Exposure Trajectory Recovery for Dynamic Blur Estimation

10/06/2020
by   Youjian Zhang, et al.
0

Dynamic scene blurring is an important yet challenging topic. Recently, deep learning methods have achieved impressive performance for dynamic scene deblurring. However, the motion information contained in a blurry image has yet to be fully explored and accurately formulated because: (i) the ground truth of blurry motion is difficult to obtain; (ii) the temporal ordering is destroyed during the exposure; and (iii) the motion estimation is highly ill-posed. By revisiting the principle of camera exposure, dynamic blur can be described by the relative motions of sharp content with respect to each exposed pixel. We define exposure trajectories, which record the trajectories of relative motions to represent the motion information contained in a blurry image and explain the causes of the dynamic blur. A new blur representation, which we call motion offset, is proposed to model pixel-wise displacements of the latent sharp image at multiple timepoints. Under mild constraints, the learned motion offsets can recover dense, (non-)linear exposure trajectories, which significantly reduce temporal disorder and ill-posed problems. Finally, we demonstrate that the estimated exposure trajectories can fit real-world dynamic blurs and further contribute to motion-aware image deblurring and warping-based video extraction from a single blurry image.

READ FULL TEXT

page 6

page 12

page 13

page 15

page 16

page 17

research
12/11/2019

Photosequencing of Motion Blur using Short and Long Exposures

Photosequencing aims to transform a motion blurred image to a sequence o...
research
08/11/2017

Video Deblurring via Semantic Segmentation and Pixel-Wise Non-Linear Kernel

Video deblurring is a challenging problem as the blur is complex and usu...
research
03/01/2019

Single Image Deblurring and Camera Motion Estimation with Depth Map

Camera shake during exposure is a major problem in hand-held photography...
research
10/20/2020

Video Reconstruction by Spatio-Temporal Fusion of Blurred-Coded Image Pair

Learning-based methods have enabled the recovery of a video sequence fro...
research
12/08/2016

From Motion Blur to Motion Flow: a Deep Learning Solution for Removing Heterogeneous Motion Blur

Removing pixel-wise heterogeneous motion blur is challenging due to the ...
research
09/16/2023

ExBluRF: Efficient Radiance Fields for Extreme Motion Blurred Images

We present ExBluRF, a novel view synthesis method for extreme motion blu...
research
08/14/2017

Learning Blind Motion Deblurring

As handheld video cameras are now commonplace and available in every sma...

Please sign up or login with your details

Forgot password? Click here to reset