Encoder Enabled GAN-based Video Generators

Jingbo Yang; Adrian Gheorghe Bors

doi:10.1109/ICIP46576.2022.9897233

Encoder Enabled GAN-based Video Generators

Jingbo Yang, Adrian Gheorghe Bors

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This research study proposes a compatible encoder-enabled video generating method. The encoder-enabled method adds an inference mechanism for enhancing the ability of Generative Adversarial Networks (GAN) based video generators. The proposed video generating method is called Encoding GAN3 (EncGAN3) and decomposes the video into two streams representing content and movement, respectively. The proposed model consists of three processing modules, representing Encoder, Generator and Discriminator, each trained separately, by considering its own loss function. EncGAN3 is shown to generate videos of high quality, according to both visual and numerical results.

Original language	English
Title of host publication	IEEE International Conference on Image Processing (ICIP)
Place of Publication	Bordeaux, France
Publisher	IEEE
Pages	1841-1845
ISBN (Print)	9781665496209
DOIs	https://doi.org/10.1109/ICIP46576.2022.9897233
Publication status	Published - 18 Oct 2022

Bibliographical note

© 2022 IEEE. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details

Access to Document

10.1109/ICIP46576.2022.9897233

ICIP2022a
© 2022 IEEE. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details
Accepted author manuscript, 4.04 MB

Cite this

@inproceedings{14b09fc1e2d843998df226b6d6e1579b,

title = "Encoder Enabled GAN-based Video Generators",

abstract = "This research study proposes a compatible encoder-enabled video generating method. The encoder-enabled method adds an inference mechanism for enhancing the ability of Generative Adversarial Networks (GAN) based video generators. The proposed video generating method is called Encoding GAN3 (EncGAN3) and decomposes the video into two streams representing content and movement, respectively. The proposed model consists of three processing modules, representing Encoder, Generator and Discriminator, each trained separately, by considering its own loss function. EncGAN3 is shown to generate videos of high quality, according to both visual and numerical results.",

author = "Jingbo Yang and Bors, {Adrian Gheorghe}",

note = "{\textcopyright} 2022 IEEE. This is an author-produced version of the published paper. Uploaded in accordance with the publisher{\textquoteright}s self-archiving policy. Further copying may not be permitted; contact the publisher for details",

year = "2022",

month = oct,

day = "18",

doi = "10.1109/ICIP46576.2022.9897233",

language = "English",

isbn = "9781665496209",

pages = "1841--1845",

booktitle = "IEEE International Conference on Image Processing (ICIP)",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Encoder Enabled GAN-based Video Generators

AU - Yang, Jingbo

AU - Bors, Adrian Gheorghe

N1 - © 2022 IEEE. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details

PY - 2022/10/18

Y1 - 2022/10/18

N2 - This research study proposes a compatible encoder-enabled video generating method. The encoder-enabled method adds an inference mechanism for enhancing the ability of Generative Adversarial Networks (GAN) based video generators. The proposed video generating method is called Encoding GAN3 (EncGAN3) and decomposes the video into two streams representing content and movement, respectively. The proposed model consists of three processing modules, representing Encoder, Generator and Discriminator, each trained separately, by considering its own loss function. EncGAN3 is shown to generate videos of high quality, according to both visual and numerical results.

AB - This research study proposes a compatible encoder-enabled video generating method. The encoder-enabled method adds an inference mechanism for enhancing the ability of Generative Adversarial Networks (GAN) based video generators. The proposed video generating method is called Encoding GAN3 (EncGAN3) and decomposes the video into two streams representing content and movement, respectively. The proposed model consists of three processing modules, representing Encoder, Generator and Discriminator, each trained separately, by considering its own loss function. EncGAN3 is shown to generate videos of high quality, according to both visual and numerical results.

U2 - 10.1109/ICIP46576.2022.9897233

DO - 10.1109/ICIP46576.2022.9897233

M3 - Conference contribution

SN - 9781665496209

SP - 1841

EP - 1845

BT - IEEE International Conference on Image Processing (ICIP)

PB - IEEE

CY - Bordeaux, France

ER -