東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

MixNMatch: Multifactor Disentangleme...

Li, Yuheng.

Linked to FindBook

Google Book

Amazon

博客來

MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation.

Record Type:	Electronic resources : Monograph/item
Title/Author:	MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation./
Author:	Li, Yuheng.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2020,
Description:	25 p.
Notes:	Source: Masters Abstracts International, Volume: 82-04.
Contained By:	Masters Abstracts International82-04.
Subject:	Computer science. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27995737
ISBN:	9798672163635

MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation.
Li, Yuheng.

MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 25 p.

Source: Masters Abstracts International, Volume: 82-04.

Thesis (M.S.)--University of California, Davis, 2020.

This item must not be sold to any third party vendors.

We present MixNMatch, a conditional generative model that learns to disentangle and encode background, object pose, shape, and texture from real images with minimal supervision, for mix-and-match image generation. We build upon FineGAN, an unconditional generative model, to learn the desired disentanglement and image generator, and leverage adversarial joint image-code distribution matching to learn the latent factor encoders. MixNMatch requires bounding boxes during training to model background, but requires no other supervision. Through extensive experiments, we demonstrate MixNMatch's ability to accurately disentangle, encode, and combine multiple factors for mix-and-match image generation, including sketch2color, cartoon2img, and img2gif applications.Our code/models/demo can be found at https://github.com/Yuheng-Li/MixNMatch.

ISBN: 9798672163635Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Disentanglement

MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation.
LDR:02029nmm a2200397 4500 001 2282792
005 20211022115945.5
008 220723s2020 ||||||||||||||||| ||eng d
020 $a 9798672163635
035 $a (MiAaPQ)AAI27995737
035 $a AAI27995737
040 $a MiAaPQ $c MiAaPQ
100 1 $a Li, Yuheng. $3 1920863
245 1 0 $a MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 25 p.
500 $a Source: Masters Abstracts International, Volume: 82-04.
500 $a Advisor: Lee, Yong Jae.
502 $a Thesis (M.S.)--University of California, Davis, 2020.
506 $a This item must not be sold to any third party vendors.
520 $a We present MixNMatch, a conditional generative model that learns to disentangle and encode background, object pose, shape, and texture from real images with minimal supervision, for mix-and-match image generation. We build upon FineGAN, an unconditional generative model, to learn the desired disentanglement and image generator, and leverage adversarial joint image-code distribution matching to learn the latent factor encoders. MixNMatch requires bounding boxes during training to model background, but requires no other supervision. Through extensive experiments, we demonstrate MixNMatch's ability to accurately disentangle, encode, and combine multiple factors for mix-and-match image generation, including sketch2color, cartoon2img, and img2gif applications.Our code/models/demo can be found at https://github.com/Yuheng-Li/MixNMatch.
590 $a School code: 0029.
650 4 $a Computer science. $3 523869
650 4 $a Design. $3 518875
650 4 $a Educational technology. $3 517670
653 $a Disentanglement
653 $a Encoding
653 $a Image generation
653 $a Image codes
653 $a sketch2color
653 $a cartoon2img
653 $a img2gif
690 $a 0984
690 $a 0389
690 $a 0710
710 2 $a University of California, Davis. $b Computer Science. $3 1671200
773 0 $t Masters Abstracts International $g 82-04.
790 $a 0029
791 $a M.S.
792 $a 2020
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27995737