ChunkyGAN: Real Image Inversion via Segments

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F22%3A00360787" target="_blank" >RIV/68407700:21230/22:00360787 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/978-3-031-20050-2_12" target="_blank" >https://doi.org/10.1007/978-3-031-20050-2_12</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-20050-2_12" target="_blank" >10.1007/978-3-031-20050-2_12</a>

Jazyk výsledku

angličtina

Název v původním jazyce

ChunkyGAN: Real Image Inversion via Segments

Popis výsledku v původním jazyce

We present ChunkyGAN—a novel paradigm for modeling and editing images using generative adversarial networks. Unlike previous techniques seeking a global latent representation of the input image, our approach subdivides the input image into a set of smaller components (chunks) specified either manually or automatically using a pre-trained segmentation network. For each chunk, the latent code of a generative network is estimated locally with greater accuracy thanks to a smaller number of constraints. Moreover, during the optimization of latent codes, segmentation can further be refined to improve matching quality. This process enables high-quality projection of the original image with spatial disentanglement that previous methods would find challenging to achieve. To demonstrate the advantage of our approach, we evaluated it quantitatively and also qualitatively in various image editing scenarios that benefit from the higher reconstruction quality and local nature of the approach. Our method is flexible enough to manipulate even out-of-domain images that would be hard to reconstruct using global techniques.

Název v anglickém jazyce

ChunkyGAN: Real Image Inversion via Segments

Popis výsledku anglicky

We present ChunkyGAN—a novel paradigm for modeling and editing images using generative adversarial networks. Unlike previous techniques seeking a global latent representation of the input image, our approach subdivides the input image into a set of smaller components (chunks) specified either manually or automatically using a pre-trained segmentation network. For each chunk, the latent code of a generative network is estimated locally with greater accuracy thanks to a smaller number of constraints. Moreover, during the optimization of latent codes, segmentation can further be refined to improve matching quality. This process enables high-quality projection of the original image with spatial disentanglement that previous methods would find challenging to achieve. To demonstrate the advantage of our approach, we evaluated it quantitatively and also qualitatively in various image editing scenarios that benefit from the higher reconstruction quality and local nature of the approach. Our method is flexible enough to manipulate even out-of-domain images that would be hard to reconstruct using global techniques.

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/EF16_019%2F0000765" target="_blank" >EF16_019/0000765: Výzkumné centrum informatiky</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2022

Kód důvěrnosti údajů

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

Název statě ve sborníku

Computer Vision – ECCV 2022, Part XXIII

ISBN

978-3-031-20049-6

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

16

Strana od-do

189-204

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Tel Aviv

Datum konání akce

23. 10. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000904146300012