别名
计算机科学
混叠
发电机(电路理论)
生成语法
人工智能
翻译(生物学)
对抗制
图像翻译
跟踪(心理语言学)
过程(计算)
计算机视觉
理论计算机科学
算法
图像(数学)
数据挖掘
功率(物理)
生物化学
物理
化学
语言学
哲学
量子力学
欠采样
信使核糖核酸
基因
操作系统
作者
Tero Karras,Miika Aittala,Samuli Laine,Erik Härkönen,Janne Hellsten,Jaakko Lehtinen,Timo Aila
出处
期刊:Cornell University - arXiv
日期:2021-06-23
被引量:10
摘要
We observe that despite their hierarchical convolutional nature, the synthesis process of typical generative adversarial networks depends on absolute pixel coordinates in an unhealthy manner. This manifests itself as, e.g., detail appearing to be glued to image coordinates instead of the surfaces of depicted objects. We trace the root cause to careless signal processing that causes aliasing in the generator network. Interpreting all signals in the network as continuous, we derive generally applicable, small architectural changes that guarantee that unwanted information cannot leak into the hierarchical synthesis process. The resulting networks match the FID of StyleGAN2 but differ dramatically in their internal representations, and they are fully equivariant to translation and rotation even at subpixel scales. Our results pave the way for generative models better suited for video and animation.
科研通智能强力驱动
Strongly Powered by AbleSci AI