English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
Add to Basket
 Local TagsRelease HistoryDetailsSummary
  Adversarial Scene Editing: Automatic Object Removal from Weak Supervision

Shetty, R., Fritz, M., & Schiele, B. (2018). Adversarial Scene Editing: Automatic Object Removal from Weak Supervision. In S. Bengio, H. Wallach, H. Larochelle, K. Graumann, N. Cesa-Bianchi, & R. Garnett (Eds.), Advances in Neural Information Processing Systems 31 (pp. 7716-7726). Curran Associates.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/21.11116/0000-0001-7A92-1 Version Permalink: https://hdl.handle.net/21.11116/0000-000E-219C-D
Genre: Conference Paper

Files

show Files

Creators

show
hide
 Creators:
Shetty, Rakshith1, Author           
Fritz, Mario2, Author           
Schiele, Bernt1, Author                 
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              
2External Organizations, ou_persistent22              

Content

show
hide
Free keywords: Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Artificial Intelligence, cs.AI,Statistics, Machine Learning, stat.ML
 Abstract: While great progress has been made recently in automatic image manipulation,
it has been limited to object centric images like faces or structured scene
datasets. In this work, we take a step towards general scene-level image
editing by developing an automatic interaction-free object removal model. Our
model learns to find and remove objects from general scene images using
image-level labels and unpaired data in a generative adversarial network (GAN)
framework. We achieve this with two key contributions: a two-stage editor
architecture consisting of a mask generator and image in-painter that
co-operate to remove objects, and a novel GAN based prior for the mask
generator that allows us to flexibly incorporate knowledge about object shapes.
We experimentally show on two datasets that our method effectively removes a
wide variety of objects using weak supervision only

Details

show
hide
Language(s): eng - English
 Dates: 2018-06-052018
 Publication Status: Published online
 Pages: 13 p.
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: NIPS2018_7997
 Degree: -

Event

show
hide
Title: Thirty-second Conference on Neural Information Processing Systems
Place of Event: Montréal, Canada
Start-/End Date: 2018-12-02 - 2018-12-08

Legal Case

show

Project information

show

Source 1

show
hide
Title: Advances in Neural Information Processing Systems 31
  Subtitle : NIPS 2018
  Abbreviation : NeurIPS 2018
Source Genre: Proceedings
 Creator(s):
Bengio, S.1, Editor
Wallach, H.1, Editor
Larochelle, H.1, Editor
Graumann, K.1, Editor
Cesa-Bianchi, N.1, Editor
Garnett, R.1, Editor
Affiliations:
1 External Organizations, ou_persistent22            
Publ. Info: Curran Associates
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 7716 - 7726 Identifier: -