Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance

07/20/2022
by   Zhihang Zhong, et al.
6

We study the challenging problem of recovering detailed motion from a single motion-blurred image. Existing solutions to this problem estimate a single image sequence without considering the motion ambiguity for each region. Therefore, the results tend to converge to the mean of the multi-modal possibilities. In this paper, we explicitly account for such motion ambiguity, allowing us to generate multiple plausible solutions all in sharp detail. The key idea is to introduce a motion guidance representation, which is a compact quantization of 2D optical flow with only four discrete motion directions. Conditioned on the motion guidance, the blur decomposition is led to a specific, unambiguous solution by using a novel two-stage decomposition network. We propose a unified framework for blur decomposition, which supports various interfaces for generating our motion guidance, including human input, motion information from adjacent video frames, and learning from a video dataset. Extensive experiments on synthesized datasets and real-world data show that the proposed framework is qualitatively and quantitatively superior to previous methods, and also offers the merit of producing physically plausible and diverse solutions. Code is available at https://github.com/zzh-tech/Animation-from-Blur.

READ FULL TEXT

page 10

page 12

page 13

page 14

page 20

page 21

research
07/27/2022

Efficient Video Deblurring Guided by Motion Magnitude

Video deblurring is a highly under-constrained problem due to the spatia...
research
11/25/2021

Exploring Versatile Prior for Human Motion via Motion Frequency Guidance

Prior plays an important role in providing the plausible constraint on h...
research
04/04/2023

HyperCUT: Video Sequence from a Single Blurry Image using Unsupervised Ordering

We consider the challenging task of training models for image-to-video d...
research
04/20/2016

Parametric Object Motion from Blur

Motion blur can adversely affect a number of vision tasks, hence it is g...
research
06/06/2023

BokehOrNot: Transforming Bokeh Effect with Image Transformer and Lens Metadata Embedding

Bokeh effect is an optical phenomenon that offers a pleasant visual expe...
research
05/29/2021

E2ETag: An End-to-End Trainable Method for Generating and Detecting Fiducial Markers

Existing fiducial markers solutions are designed for efficient detection...
research
09/22/2022

UniColor: A Unified Framework for Multi-Modal Colorization with Transformer

We propose the first unified framework UniColor to support colorization ...

Please sign up or login with your details

Forgot password? Click here to reset