DeFMO: Deblurring and Shape Recovery of Fast Moving Objects

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F21%3A00354082" target="_blank" >RIV/68407700:21230/21:00354082 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.1109/CVPR46437.2021.00346" target="_blank" >https://doi.org/10.1109/CVPR46437.2021.00346</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/CVPR46437.2021.00346" target="_blank" >10.1109/CVPR46437.2021.00346</a>

Result language

angličtina

Original language name

DeFMO: Deblurring and Shape Recovery of Fast Moving Objects

Original language description

Objects moving at high speed appear significantly blurred when captured with cameras. The blurry appearance is especially ambiguous when the object has complex shape or texture. In such cases, classical methods, or even humans, are unable to recover the object's appearance and motion. We propose a method that, given a single image with its estimated background, outputs the object's appearance and position in a series of sub-frames as if captured by a high-speed camera (i.e. temporal super-resolution). The proposed generative model embeds an image of the blurred object into a latent space representation, disentangles the background, and renders the sharp appearance. Inspired by the image formation model, we design novel self-supervised loss function terms that boost performance and show good generalization capabilities. The proposed DeFMO method is trained on a complex synthetic dataset, yet it performs well on real-world data from several datasets. DeFMO outperforms the state of the art and generates high-quality temporal super-resolution frames.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/GA18-05360S" target="_blank" >GA18-05360S: Solving inverse problems for the analysis of fast moving objects</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2021

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

ISBN

978-1-6654-4509-2

ISSN

1063-6919

e-ISSN

2575-7075

Number of pages

10

Pages from-to

3455-3464

Publisher name

IEEE Computer Society

Place of publication

USA

Event location

Nashville

Event date

Jun 20, 2021

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

000739917303064