返回
Image generation with self pixel-wise normalization
DOI:10.1007/s10489-022-04007-z.png)
摘要
En 中文
Region-adaptive normalization (RAN) methods have been widely used in the generative adversarial network (GAN)-based image-to-image translation technique. However, since these approaches need a mask image to infer pixel-wise affine transformation parameters, they are not applicable to general image generation models having no paired mask images. To resolve this problem, this paper presents a novel normalization method, called self pixel-wise normalization (SPN), which effectively boosts the generative performance by carrying out the pixel-adaptive affine transformation without an external guidance map. In our method, the transforming parameters are derived from a self-latent mask that divides the feature map into foreground and background regions. The visualization of the self-latent masks shows that SPN effectively captures a single object to be generated as the foreground. Since the proposed method produces the self-latent mask without external data, it is easily adaptable to existing generative models. Extensive experiments on various datasets reveal that our SPN significantly improves the performance of image generation technique in terms of Frechet inception distance (FID) and Inception score (IS).
Keyword:
Generative adversarial networks
Image generation
Normalization
Region-adaptive normalization
期刊
IF:
3.5
论文数:
7.6K
被引数:
1.7W
机构
引用论文
Caw’s Walking State Recognition Based on Accelerometers and Gyroscopes Installed on Ear-Tags and Collar-Tags基于安装在耳标和项圈上的加速度计和陀螺仪的Caw步行状态识别
The Effect of 40-Hz Light Therapy on Amyloid Load in Patients with Prodromal and Clinical Alzheimer’s Disease40Hz光疗法对前驱和临床阿尔茨海默病患者淀粉样蛋白负荷的影响
Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系?

