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 …

Common image-to-image translation methods rely on joint training over data from both
source and target domains. The training process requires concurrent access to both …

In this work, we tackle the challenging problem of arbitrary image style transfer using a novel
style feature representation learning method. A suitable style representation, as a key …

State-of-the-art parametric and non-parametric style transfer approaches are prone to either
distorted local style patterns due to global statistics alignment, or unpleasing artifacts …

Controllable person image synthesis task enables a wide range of applications through
explicit control over body pose and appearance. In this paper, we propose a cross attention …

The mechanism of existing style transfer algorithms is by minimizing a hybrid loss function to
push the generated image toward high similarities in both content and style. However, this …

This work presents Unified Contrastive Arbitrary Style Transfer (UCAST), a novel style
representation learning and transfer framework, that can fit in most existing arbitrary image …

Arbitrary style transfer has been demonstrated to be efficient in artistic image generation.
Previous methods either globally modulate the content feature ignoring local details, or …

Diffusion models have recently become increasingly popular in a number of computer vision
tasks but they fail to achieve satisfactory results for unsupervised image-to-image translation …

The field of neural style transfer has experienced a surge of research exploring different
avenues ranging from optimization-based approaches and feed-forward models to meta …