6 papers
On Denoising Walking Videos for Gait Recognition
Dongyang Jin, Chao Fan, Jingzhe Ma +3
To capture individual gait patterns, excluding identity-irrelevant cues in walking videos, such as clothing texture and color, remains a persistent challenge for vision-based gait…
RealisDance-DiT: Simple yet Strong Baseline towards Controllable Character Animation in the Wild
Jingkai Zhou, Yifan Wu, Shikai Li +5
Controllable character animation remains a challenging problem, particularly in handling rare poses, stylized characters, character-object interactions, complex illumination, and d…
RealisID: Scale-Robust and Fine-Controllable Identity Customization via Local and Global Complementation
Zhaoyang Sun, Fei Du, Weihua Chen +4
Recently, the success of text-to-image synthesis has greatly advanced the development of identity customization techniques, whose main goal is to produce realistic identity-specifi…
Exploring More from Multiple Gait Modalities for Human Identification
Dongyang Jin, Chao Fan, Weihua Chen +1
The gait, as a kind of soft biometric characteristic, can reflect the distinct walking patterns of individuals at a distance, exhibiting a promising technique for unrestrained huma…
SHMT: Self-supervised Hierarchical Makeup Transfer via Latent Diffusion Models
Zhaoyang Sun, Shengwu Xiong, Yaxiong Chen +4
This paper studies the challenging task of makeup transfer, which aims to apply diverse makeup styles precisely and naturally to a given facial image. Due to the absence of paired…
RealisHuman: A Two-Stage Approach for Refining Malformed Human Parts in Generated Images
Benzhi Wang, Jingkai Zhou, Jingqi Bai +4
In recent years, diffusion models have revolutionized visual generation, outperforming traditional frameworks like Generative Adversarial Networks (GANs). However, generating image…