Although arbitrary style transfer has been a hot topic in computer vision, most existing
methods that directly align style and content features frequently result in unnatural effects in …

Generative Adversarial Network (GAN)-based image cartoonization has made great
progress. They usually use a “single-encoding adversarial feedback architecture” to …

Existing pulmonary nodule detection methods often train models in a fully-supervised setting
that requires strong labels (ie, bounding box labels) as label information. However, manual …

Few-shot font generation (FFG) aims to preserve the underlying global structure of the
original character while generating target fonts by referring to a few samples. It has been …

Most arbitrary style transfer methods only consider transferring the features of the style and
content images. Although the pixel-wise style transfer is achieved. It is limited to preserving …

Pan-sharpening aims to generate high-detail multi-spectral images (HRMS) through the
fusion of panchromatic (PAN) and multi-spectral (MS) images. However, existing pan …

The term “ambiguous sketchy image” refers to images comprising abstract lines. In such
images, unclear semantics and weak semantics often occur. Stylizing such ambiguous …

Style transfer presents a significant challenge, primarily centered on identifying an
appropriate style representation. Conventional methods employ style loss, derived from …

The discrepancy in data distribution between training and testing scenarios, as well as the
inductive bias of convolutional neural networks towards image styles, reduces the model's …