collaborators

6 papers

cs.CV2025

AvatarVTON: 4D Virtual Try-On for Animatable Avatars

Zicheng Jiang, Jixin Gao, Shengfeng He +5

We propose AvatarVTON, the first 4D virtual try-on framework that generates realistic try-on results from a single in-shop garment image, enabling free pose control, novel-view ren…

cs.CV2025

Cross-Subject Mind Decoding from Inaccurate Representations

Yangyang Xu, Bangzhen Liu, Wenqi Shao +3

Decoding stimulus images from fMRI signals has advanced with pre-trained generative models. However, existing methods struggle with cross-subject mappings due to cognitive variabil…

cs.CV2025

HarmonPaint: Harmonized Training-Free Diffusion Inpainting

Ying Li, Xinzhe Li, Yong Du +3

Existing inpainting methods often require extensive retraining or fine-tuning to integrate new content seamlessly, yet they struggle to maintain coherence in both structure and sty…

cs.CV2025

OmniVTON: Training-Free Universal Virtual Try-On

Zhaotong Yang, Yuhui Li, Shengfeng He +4

Image-based Virtual Try-On (VTON) techniques rely on either supervised in-shop approaches, which ensure high fidelity but struggle with cross-domain generalization, or unsupervised…

cs.CV2025

Stable Score Distillation

Haiming Zhu, Yangyang Xu, Chenshu Xu +5

Text-guided image and 3D editing have advanced with diffusion-based models, yet methods like Delta Denoising Score often struggle with stability, spatial control, and editing stren…

cs.CV2024

PersonaMagic: Stage-Regulated High-Fidelity Face Customization with Tandem Equilibrium

Xinzhe Li, Jiahui Zhan, Shengfeng He +4

Personalized image generation has made significant strides in adapting content to novel concepts. However, a persistent challenge remains: balancing the accurate reconstruction of…