Delving into Rectifiers in Style-Based Image Translation
While modern image translation techniques can create photorealistic synthetic images, they have limited style controllability, thus could suffer from translation errors. In this work, we show that the activation function is one of the crucial components in controlling the direction of image synthesis. Specifically, we explicitly demonstrated that the slope parameters of the rectifier could change the data distribution and be used independently to control the direction of translation. To improve the style controllability, two simple but effective techniques are proposed, including Adaptive ReLU (AdaReLU) and structural adaptive function. The AdaReLU can dynamically adjust the slope parameters according to the target style and can be utilized to increase the controllability by combining with Adaptive Instance Normalization (AdaIN). Meanwhile, the structural adaptative function enables rectifiers to manipulate the structure of feature maps more effectively. It is composed of the proposed structural convolution (StruConv), an efficient convolutional module that can choose the area to be activated based on the mean and variance specified by AdaIN. Extensive experiments show that the proposed techniques can greatly increase the network controllability and output diversity in style-based image translation tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityImage GenerationTranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
Rectified activation units (rectifiers) are essential for state-of-the-art neural networks. In this work, we study rectifier neural networks for image classification from two aspects. First, we propose a Parametric Recti…
General Classificationimage-classificationImage ClassificationOptimal Switching of Controlled Rectifiers
This paper discusses a linear programming approach for designing switching signals for controlled rectifiers to achieve a low input current & output voltage total harmonic distortions. The focus here is on fully controll…
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
We present a generic image-to-image translation framework, pixel2style2pixel (pSp). Our pSp framework is based on a novel encoder network that directly generates a series of style vectors which are fed into a pretrained …
Conditional Image GenerationFace GenerationImage-to-Image TranslationTranslationExploring the Power of Generative Deep Learning for Image-to-Image Translation and MRI Reconstruction: A Cross-Domain Review
Deep learning has become a prominent computational modeling tool in the areas of computer vision and image processing in recent years. This research comprehensively analyzes the different deep-learning methods used for i…
Deep LearningImage-to-Image TranslationMRI ReconstructionTranslationStyleFlow For Content-Fixed Image to Image Translation
Image-to-image (I2I) translation is a challenging topic in computer vision. We divide this problem into three tasks: strongly constrained translation, normally constrained translation, and weakly constrained translation.…
ColorizationImage-to-Image TranslationStyle TransferTranslation