Jianfu Zhang

FlowVVTON achieves a groundbreaking 5.7× improvement in temporal consistency for video virtual try-on without relying on any segmentation masks or pose keypoints.

Existing detectors fail to maintain critical visual information, but a new two-stage approach achieves unprecedented accuracy in distinguishing real from fake 3D faces.

Defake-o3 transforms AIGI detection by replacing vague explanations with verifiable evidence, significantly enhancing both accuracy and interpretability.

Reconstruct a high-fidelity, full-head 3D avatar from a single image in under one second, finally breaking the quality-speed tradeoff.