Conference item icon

Conference item

Depth-SIMS: semi-parametric image and depth synthesis

Abstract:
In this paper we present a compositing image synthesis method that generates RGB canvases with well aligned segmentation maps and sparse depth maps, coupled with an in-painting network that transforms the RGB canvases into high quality RGB images and the sparse depth maps into pixel-wise dense depth maps. We benchmark our method in terms of structural alignment and image quality, showing an increase in mIoU over SOTA by 3.7 percentage points and a highly competitive FID. Furthermore, we analyse the quality of the generated data as training data for semantic segmentation and depth completion, and show that our approach is more suited for this purpose than other methods.
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1109/ICRA46639.2022.9811569

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author


Publisher:
IEEE
Host title:
2022 International Conference on Robotics and Automation (ICRA)
Pages:
2388-2394
Publication date:
2022-07-12
Acceptance date:
2022-01-31
Event title:
International Conference on Robotics and Automation (ICRA 2022)
Event location:
Philadelphia, USA
Event website:
https://www.icra2022.org/
Event start date:
2022-05-23
Event end date:
2022-05-27
DOI:
EISBN:
9781728196817
ISBN:
9781728196824


Language:
English
Keywords:
Pubs id:
1242881
Local pid:
pubs:1242881
Deposit date:
2022-03-09

Terms of use



Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP