Yifan Ruan
Papers
1
Total Citations
10
H-Index
1
About
Yifan Ruan is a researcher advancing the frontier of 3D shape understanding and geometric modeling, with a core focus on unsupervised learning for part-segmented shape collections. His most notable contribution is the development of a pioneering method for unsupervised kinematic motion detection in 3D objects, enabling the automatic discovery of how object parts move—such as hinges, sliders, or rotations—without requiring any labeled training data. This work, published in 2022 and garnering 10 citations, directly addresses a critical bottleneck in computer graphics and robotics: the labor-intensive process of manually creating articulated 3D models for virtual worlds and synthetic data generation. By allowing machines to infer motion from static shape collections, Ruan’s research promises to dramatically scale the creation of realistic, interactive objects for simulation and embodied AI. His approach stands out for its ability to learn motion patterns purely from geometric and structural cues, offering a scalable alternative to hand-crafted annotations. Ruan’s contributions are particularly impactful for researchers in shape analysis, scene understanding, and robotic manipulation, where accessible, articulated 3D assets are increasingly vital.
Research Focus
Key Achievements
Top Papers
- 1