Adversarial Generation of Continuous Images
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021(2021)
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.
更多查看译文
关键词
INR-based decoders,meaningful image-space interpolation,low-resolution images,image boundaries,adversarial generation,2D pixel arrays,implicit neural representation,RGB pixel value,INR-based image decoders,factorized multiplicative modulation,image generation,INR-GAN architecture,continuous image generators,continuous image GAN,multiscale INR,out-of-the-box superresolution,image-space interpolation,low-resolution image accelerated inference
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络