Rujing Wang

Papers

Total Citations

H-Index

About

Rujing Wang is a rising researcher in computer vision and robotics, with a primary focus on 3D perception and articulated object manipulation. Their most notable contribution is the development of VoCAPTER, a voting-based pose tracking framework for category-level articulated objects. This work addresses the challenging problem of online, robust 9D pose tracking for objects with moving parts—such as cabinets, drawers, and doors—using inter-frame priors to achieve stable, real-time performance. Although published in 2024, this paper has already garnered 4 citations, signaling early impact in a rapidly evolving field. Wang’s research bridges the gap between static object pose estimation and dynamic, articulated object tracking, which is critical for applications in service robotics, augmented reality, and autonomous manipulation. By introducing a voting mechanism that leverages temporal consistency, Wang has advanced the robustness and accuracy of category-level pose tracking, moving beyond traditional single-frame predictions. Their work stands out for its practical relevance to everyday environments, where articulated objects are ubiquitous. As an emerging scholar, Rujing Wang is poised to make further strides in embodied AI and interactive perception, offering valuable insights for students and researchers interested in the intersection of 3D vision and robotic interaction.