Program-Guided Image Manipulators
Name
1909.02116.pdf
Description
Accepted version
Size
5.68 MB
Format
Unknown
Checksum (MD5)
aaab352da9e727a4021c149f864a2a54
Author(s)
Mao, Jiayuan
Zhang, Xiuming
Li, Yikai
Freeman, William T
Tenenbaum, Joshua B
Wu, Jiajun
Date Issued
September 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.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/ICCV.2019.00413
