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

TL;DR

This paper introduces a novel framework for recovering detailed, multiple plausible motion solutions from a single blurred image by using a motion guidance representation and a two-stage decomposition network.

Contribution

It explicitly models motion ambiguity with a compact motion guidance, enabling unambiguous and diverse motion deblurring solutions from a single image.

Findings

Outperforms previous methods on synthesized and real data

Produces physically plausible and diverse motion reconstructions

Supports various interfaces for generating motion guidance

Abstract

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.