DeFMO: Deblurring and Shape Recovery of Fast Moving Objects

Kód výsledku v 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>

Výsledek na webu

<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>

Jazyk výsledku

angličtina

Název v původním jazyce

DeFMO: Deblurring and Shape Recovery of Fast Moving Objects

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

DeFMO: Deblurring and Shape Recovery of Fast Moving Objects

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

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

Projekt

<a href="/cs/project/GA18-05360S" target="_blank" >GA18-05360S: Řešení inverzních problémů vznikajících při analýze rychle se pohybujících objektů</a><br>

Návaznosti

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

Rok uplatnění

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

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

Počet stran výsledku

10

Strana od-do

3455-3464

Název nakladatele

IEEE Computer Society

Místo vydání

USA

Místo konání akce

Nashville

Datum konání akce

20. 6. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000739917303064