Shapes and Context: In-the-Wild Image Synthesis & Manipulation
We introduce a data-driven approach for interactively synthesizing in-the-wild images from semantic label maps. Our approach is dramatically different from recent work in this space, in that we make use of no learning. Instead, our approach uses simple but classic tools for matching scene context, shapes, and parts to a stored library of exemplars. Though simple, this approach has several notable advantages over recent work: (1) because nothing is learned, it is not limited to specific training data distributions (such as cityscapes, facades, or faces); (2) it can synthesize arbitrarily high-resolution images, limited only by the resolution of the exemplar library; (3) by appropriately composing shapes and parts, it can generate an exponentially large set of viable candidate output images (that can say, be interactively searched by a user). We present results on the diverse COCO dataset, significantly outperforming learning-based approaches on standard image synthesis metrics. Finally, we explore user-interaction and user-controllability, demonstrating that our system can be used as a platform for user-driven content creation.
NurtureToken New!

Token crowdsale for this paper ends in

Buy Nurture Tokens

Authors

Are you an author of this paper? Check the Twitter handle we have for you is correct.

Aayush Bansal (edit)
Yaser Sheikh (add twitter)
Deva Ramanan (add twitter)
Ask The Authors

Ask the authors of this paper a question or leave a comment.

Read it. Rate it.
#1. Which part of the paper did you read?

#2. The paper contains new data or analyses that is openly accessible?
#3. The conclusion is supported by the data and analyses?
#4. The conclusion is of scientific interest?
#5. The result is likely to lead to future research?

Github
User:
None (add)
Repo:
None (add)
Stargazers:
0
Forks:
0
Open Issues:
0
Network:
0
Subscribers:
0
Language:
None
Youtube
Link:
None (add)
Views:
0
Likes:
0
Dislikes:
0
Favorites:
0
Comments:
0
Other
Sample Sizes (N=):
Inserted:
Words Total:
Words Unique:
Source:
Abstract:
None
06/11/19 06:01PM
6,508
2,132
Tweets
EricKuy: RT @roadrunning01: Shapes and Context: In-the-Wild Image Synthesis & Manipulation pdf: https://t.co/QKZgZyEmOI abs: https://t.co/6SXbW0wMYn…
aayushbansal: RT @roadrunning01: Shapes and Context: In-the-Wild Image Synthesis & Manipulation pdf: https://t.co/QKZgZyEmOI abs: https://t.co/6SXbW0wMYn…
semiinvariant: RT @roadrunning01: Shapes and Context: In-the-Wild Image Synthesis & Manipulation pdf: https://t.co/QKZgZyEmOI abs: https://t.co/6SXbW0wMYn…
arxiv_cscv: Shapes and Context: In-the-Wild Image Synthesis & Manipulation https://t.co/evxQfmOiPm
Pol09122455: RT @roadrunning01: Shapes and Context: In-the-Wild Image Synthesis & Manipulation pdf: https://t.co/QKZgZyEmOI abs: https://t.co/6SXbW0wMYn…
arxiv_cscv: Shapes and Context: In-the-Wild Image Synthesis & Manipulation https://t.co/evxQfmwHXO
heghbalz: RT @roadrunning01: Shapes and Context: In-the-Wild Image Synthesis & Manipulation pdf: https://t.co/QKZgZyEmOI abs: https://t.co/6SXbW0wMYn…
balicea1: RT @roadrunning01: Shapes and Context: In-the-Wild Image Synthesis & Manipulation pdf: https://t.co/QKZgZyEmOI abs: https://t.co/6SXbW0wMYn…
UkiwhY: RT @roadrunning01: Shapes and Context: In-the-Wild Image Synthesis & Manipulation pdf: https://t.co/QKZgZyEmOI abs: https://t.co/6SXbW0wMYn…
kodai_nakashima: RT @roadrunning01: Shapes and Context: In-the-Wild Image Synthesis & Manipulation pdf: https://t.co/QKZgZyEmOI abs: https://t.co/6SXbW0wMYn…
SythonUK: RT @roadrunning01: Shapes and Context: In-the-Wild Image Synthesis & Manipulation pdf: https://t.co/QKZgZyEmOI abs: https://t.co/6SXbW0wMYn…
sei_shinagawa: RT @roadrunning01: Shapes and Context: In-the-Wild Image Synthesis & Manipulation pdf: https://t.co/QKZgZyEmOI abs: https://t.co/6SXbW0wMYn…
roadrunning01: Shapes and Context: In-the-Wild Image Synthesis & Manipulation pdf: https://t.co/QKZgZyEmOI abs: https://t.co/6SXbW0wMYn code: https://t.co/p77UO8mQpQ video: https://t.co/XRit8XlZFK https://t.co/NXLVSw96PX
BrundageBot: Shapes and Context: In-the-Wild Image Synthesis & Manipulation. Aayush Bansal, Yaser Sheikh, and Deva Ramanan https://t.co/PiXjXOb05E
arxiv_cscv: Shapes and Context: In-the-Wild Image Synthesis & Manipulation https://t.co/evxQfmwHXO
Images
Related