This is not the latest version of this item. The latest version can be found here.
Program-Guided Image Manipulators
Name
1909.02116.pdf
Description
Accepted version
Size
5.68 MB
Format
Adobe PDF
Checksum (MD5)
aaab352da9e727a4021c149f864a2a54
Author(s)
Zhang, Xiuming
Mao, Jiayuan
Li, Yikai
Freeman, William
Tenenbaum, Joshua
Wu, Jiajun
Date Issued
2019
Journal
Proceedings of the IEEE International Conference on Computer Vision
Publisher
IEEE
Citation
Zhang, Xiuming, Mao, Jiayuan, Li, Yikai, Freeman, William, Tenenbaum, Joshua et al. 2019. "Program-Guided Image Manipulators." Proceedings of the IEEE International Conference on Computer Vision, 2019-October.
Version
Author's final manuscript
Abstract
© 2019 IEEE. Humans are capable of building holistic representations for images at various levels, from local objects, to pairwise relations, to global structures. The interpretation of structures involves reasoning over repetition and symmetry of the objects in the image. In this paper, we present the Program-Guided Image Manipulator (PG-IM), inducing neuro-symbolic program-like representations to represent and manipulate images. Given an image, PG-IM detects repeated patterns, induces symbolic programs, and manipulates the image using a neural network that is guided by the program. PG-IM learns from a single image, exploiting its internal statistics. Despite trained only on image inpainting, PG-IM is directly capable of extrapolation and regularity editing in a unified framework. Extensive experiments show that PG-IM achieves superior performance on all the tasks.
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
10.1109/ICCV.2019.00413
