Adversarial Generation of Continuous Images

被引:72
作者
Skorokhodov, Ivan [1 ]
Ignatyev, Savva [2 ]
Elhoseiny, Mohamed [1 ]
机构
[1] King Abdullah Univ Sci & Technol KAUST, Thuwal, Saudi Arabia
[2] Skolkovo Inst Sci & Technol, Moscow, Russia
来源
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 | 2021年
关键词
D O I
10.1109/CVPR46437.2021.01061
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In most existing learning systems, images are typically viewed as 2D pixel arrays. However, in another paradigm gaining popularity, a 2D image is represented as an implicit neural representation (INR) - an MLP that predicts an RGB pixel value given its (x, y) coordinate. In this paper, we propose two novel architectural techniques for building INR-based image decoders: factorized multiplicative modulation and multi-scale INRs, and use them to build a state-of-the-art continuous image GAN. Previous attempts to adapt INRs for image generation were limited to MNIST-like datasets and do not scale to complex real-world data. Our proposed INR-GAN architecture improves the performance of continuous image generators by several times, greatly reducing the gap between continuous image GANs and pixel-based ones. Apart from that, we explore several exciting properties of the INR-based decoders, like out-of-the-box superresolution, meaningful image-space interpolation, accelerated inference of low-resolution images, an ability to extrapolate outside of image boundaries, and strong geometric prior. The project page is located at https://universome.github.io/inr-gan.
引用
收藏
页码:10748 / 10759
页数:12
相关论文
共 93 条
[91]  
Zafeirouli K., 2019, INT ICE CONF ENG, P1
[92]  
Zhang Chris, 2019, P INT C LEARN REPR
[93]   Additives Control the Stability of Amorphous Calcium Carbonate via Two Different Mechanisms: Surface Adsorption versus Bulk Incorporation [J].
Zou, Zhaoyong ;
Yang, Xiaofei ;
Alberic, Marie ;
Heil, Tobias ;
Wang, Qihang ;
Pokroy, Boaz ;
Politi, Yael ;
Bertinetti, Luca .
ADVANCED FUNCTIONAL MATERIALS, 2020, 30 (23)