人工智能
计算机科学
仿射变换
卷积神经网络
模式识别(心理学)
计算机视觉
纹理(宇宙学)
图像分辨率
图像纹理
转化(遗传学)
特征(语言学)
先验概率
图像(数学)
图像分割
数学
哲学
贝叶斯概率
化学
纯数学
基因
生物化学
语言学
作者
Xintao Wang,Ke Yu,Chao Dong,Chen Change Loy
标识
DOI:10.1109/cvpr.2018.00070
摘要
Despite that convolutional neural networks (CNN) have recently demonstrated high-quality reconstruction for single-image super-resolution (SR), recovering natural and realistic texture remains a challenging problem. In this paper, we show that it is possible to recover textures faithful to semantic classes. In particular, we only need to modulate features of a few intermediate layers in a single network conditioned on semantic segmentation probability maps. This is made possible through a novel Spatial Feature Transform (SFT) layer that generates affine transformation parameters for spatial-wise feature modulation. SFT layers can be trained end-to-end together with the SR network using the same loss function. During testing, it accepts an input image of arbitrary size and generates a high-resolution image with just a single forward pass conditioned on the categorical priors. Our final results show that an SR network equipped with SFT can generate more realistic and visually pleasing textures in comparison to state-of-the-art SRGAN [27] and EnhanceNet [38].
科研通智能强力驱动
Strongly Powered by AbleSci AI