To ensure good performance, modern machine learning models typically require large
amounts of quality annotated data. Meanwhile, the data collection and annotation processes …

Normalization techniques are essential for accelerating the training and improving the
generalization of deep neural networks (DNNs), and have successfully been used in various …

The artistic style within a painting is the means of expression, which includes not only the
painting material, colors, and brushstrokes, but also the high-level attributes, including …

Can a generative model be trained to produce images from a specific domain, guided only
by a text prompt, without seeing any image? In other words: can an image generator be …

We present a method for transferring the artistic features of an arbitrary style image to a 3D
scene. Previous methods that perform 3D stylization on point clouds or meshes are sensitive …

Fast arbitrary neural style transfer has attracted widespread attention from academic,
industrial and art communities due to its flexibility in enabling various applications. Existing …

Arbitrary style transfer (AST) and domain generalization (DG) are important yet challenging
visual learning tasks, which can be cast as a feature distribution matching problem. With the …

Existing deep learning based de-raining approaches have resorted to the convolutional
architectures. However, the intrinsic limitations of convolution, including local receptive fields …

Existing neural style transfer methods require reference style images to transfer texture
information of style images to content images. However, in many practical situations, users …

Abstract 3D scene stylization aims at generating stylized images of the scene from arbitrary
novel views following a given set of style examples, while ensuring consistency when …