Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Synthesizing Images of Humans in Unseen Poses #5

Closed
ichiki-san opened this issue Jul 9, 2018 · 2 comments
Closed

Synthesizing Images of Humans in Unseen Poses #5

ichiki-san opened this issue Jul 9, 2018 · 2 comments
Assignees
@ichiki-san
Labels
2018 CVPR Image pose2img Segmentation UNet

Comments

@ichiki-san
Copy link
Collaborator

https://arxiv.org/abs/1804.07739

What

人間のSource Imageと変えたい姿勢のTarget Pose（棒人間で身体のパーツが分けられた素材）をInputに入れると、人間がその姿勢をしている画像が生成される。
人物を取り除いた背景画像と、姿勢を変えた人物の画像をそれぞれ予測し、組み合わせて画像を生成してる？
pose2img系の最新。

Why

CVPR2018の論文紹介のツイートで面白そうだったので。
@ichiki-san ichiki-san self-assigned this Jul 9, 2018
@ichiki-san
Copy link
Collaborator Author

日本語で所感をまとめたgitがあった
DwangoMediaVillage/paper_readings#41
というかこれくらいしか日本語の情報がなかった

ichiki-san added a commit that referenced this issue Jul 10, 2018
@ichiki-san
add: add #5
cbde76f
@sanshin5050
Copy link
Collaborator

複雑な問題をかみ砕いて一つ一つ処理するだけで論文になるってやっぱ基礎力大事やなと
基礎ができて論理的思考ができればこういう論文かけそうやな

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@ichiki-san ichiki-san

Labels
2018 CVPR Image pose2img Segmentation UNet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@sanshin5050 @ichiki-san