Single-Image Deblurring, Trajectory and Shape Recovery of Fast Moving Objects with Denoising Diffusion Probabilistic Models

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00376639" target="_blank" >RIV/68407700:21230/24:00376639 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/WACV57701.2024.00671" target="_blank" >http://dx.doi.org/10.1109/WACV57701.2024.00671</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/WACV57701.2024.00671" target="_blank" >10.1109/WACV57701.2024.00671</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Single-Image Deblurring, Trajectory and Shape Recovery of Fast Moving Objects with Denoising Diffusion Probabilistic Models

Popis výsledku v původním jazyce

Blurry appearance of fast moving objects in video frames was successfully used to reconstruct the object appearance and motion in both 2D and 3D domains. The proposed method addresses the novel, severely ill-posed, task of single-image fast moving object deblurring, shape, and trajectory recovery--previous approaches require at least three consecutive video frames. Given a single image, the method outputs the object 2D appearance and position in a series of sub-frames as if captured by a high-speed camera (ie temporal super-resolution). The proposed SI-DDPM-FMO method is trained end-to-end on a synthetic dataset with various moving objects, yet it generalizes well to real-world data from several publicly available datasets. SI-DDPM-FMO performs similarly to or better than recent multi-frame methods and a carefully designed baseline method.

Název v anglickém jazyce

Single-Image Deblurring, Trajectory and Shape Recovery of Fast Moving Objects with Denoising Diffusion Probabilistic Models

Popis výsledku anglicky

Blurry appearance of fast moving objects in video frames was successfully used to reconstruct the object appearance and motion in both 2D and 3D domains. The proposed method addresses the novel, severely ill-posed, task of single-image fast moving object deblurring, shape, and trajectory recovery--previous approaches require at least three consecutive video frames. Given a single image, the method outputs the object 2D appearance and position in a series of sub-frames as if captured by a high-speed camera (ie temporal super-resolution). The proposed SI-DDPM-FMO method is trained end-to-end on a synthetic dataset with various moving objects, yet it generalizes well to real-world data from several publicly available datasets. SI-DDPM-FMO performs similarly to or better than recent multi-frame methods and a carefully designed baseline method.

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

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název statě ve sborníku

2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

ISBN

979-8-3503-1892-0

ISSN

2472-6737

e-ISSN

2642-9381

Počet stran výsledku

10

Strana od-do

6843-6852

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

Waikoloa, HI, USA

Datum konání akce

4. 1. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001222964606095