7 papers
Anchoring on Reality: Breaking the Pseudo-Target Ceiling in Makeup Transfer
Bo Wei, Xianhui Lin, Yi Dong +8
Makeup transfer applies a reference cosmetic style to a source face while preserving its identity and geometry. However, this task is severely hindered by the lack of real paired t…
HDRFace: Rethinking Face Restoration with High-Dimensional Representation
Zirui Wang, Xianhui Lin, Yi Dong +7
Face restoration under complex degradations still remains an ill-posed inverse problem due to severe information loss. Although diffusion models benefit from strong generative prio…
SynerMedGen: Synergizing Medical Multimodal Understanding with Generation via Task Alignment
Weiren Zhao, Yi Dong, Cheng Chen
Unifying multimodal understanding and generation is a compelling frontier that is beginning to emerge in the medical field. However, the limited existing unified medical models typ…
BeautyGRPO: Aesthetic Alignment for Face Retouching via Dynamic Path Guidance and Fine-Grained Preference Modeling
Jiachen Yang, Xianhui Lin, Yi Dong +4
Face retouching requires removing subtle imperfections while preserving unique facial identity features, in order to enhance overall aesthetic appeal. However, existing methods suf…
Hand2World: Autoregressive Egocentric Interaction Generation via Free-Space Hand Gestures
Yuxi Wang, Wenqi Ouyang, Tianyi Wei +3
Egocentric interactive world models are essential for augmented reality and embodied AI, where visual generation must respond to user input with low latency, geometric consistency,…
I2VEdit: First-Frame-Guided Video Editing via Image-to-Video Diffusion Models
Wenqi Ouyang, Yi Dong, Lei Yang +2
The remarkable generative capabilities of diffusion models have motivated extensive research in both image and video editing. Compared to video editing which faces additional chall…
Multi-Modal Face Stylization with a Generative Prior
Mengtian Li, Yi Dong, Minxuan Lin +3
In this work, we introduce a new approach for face stylization. Despite existing methods achieving impressive results in this task, there is still room for improvement in generatin…