67 citations · 117 across the 8 of their papers we have counts for
9 papers
Bringing Diversity from Diffusion Models to Semantic-Guided Face Asset Generation
Yunxuan Cai, Sitao Xiang, Zongjian Li +2
Digital modeling and reconstruction of human faces serve various applications. However, its availability is often hindered by the requirements of data capturing devices, manual lab…
Texturize a GAN Using a Single Image
Pengda Xiang, Sitao Xiang, Yajie Zhao
Can we customize a deep generative model which can generate images that can match the texture of some given image? When you see an image of a church, you may wonder if you can get…
DisUnknown: Distilling Unknown Factors for Disentanglement Learning
Sitao Xiang, Yuming Gu, Pengda Xiang +4
Disentangling data into interpretable and independent factors is critical for controllable generation tasks. With the availability of labeled data, supervision can help enforce the…
Revisiting the Continuity of Rotation Representations in Neural Networks
Sitao Xiang, Hao Li
In this paper, we provide some careful analysis of certain pathological behavior of Euler angles and unit quaternions encountered in previous works related to rotation representati…
Generative Tweening: Long-term Inbetweening of 3D Human Motions
Yi Zhou, Jingwan Lu, Connelly Barnes +3
The ability to generate complex and realistic human body animations at scale, while following specific artistic constraints, has been a fundamental goal for the game and animation…
One-Shot Identity-Preserving Portrait Reenactment
Sitao Xiang, Yuming Gu, Pengda Xiang +4
We present a deep learning-based framework for portrait reenactment from a single picture of a target (one-shot) and a video of a driving subject. Existing facial reenactment metho…
Disentangling Style and Content in Anime Illustrations
Sitao Xiang, Hao Li
Existing methods for AI-generated artworks still struggle with generating high-quality stylized content, where high-level semantics are preserved, or separating fine-grained styles…
Anime Style Space Exploration Using Metric Learning and Generative Adversarial Networks
Sitao Xiang, Hao Li
Deep learning-based style transfer between images has recently become a popular area of research. A common way of encoding "style" is through a feature representation based on the…
On the Effects of Batch and Weight Normalization in Generative Adversarial Networks
Sitao Xiang, Hao Li
Generative adversarial networks (GANs) are highly effective unsupervised learning frameworks that can generate very sharp data, even for data such as images with complex, highly mu…