Papers
2
Total Citations
20
H-Index
2
About
Renjiao Yi is a rising researcher in computer vision and robotics, whose work bridges the gap between perception and autonomous action. Her primary research areas include template matching, 3D scene understanding, and robotic path planning. In her highly cited 2024 paper, "Learning accurate template matching with differentiable coarse-to-fine correspondence refinement," Yi tackles a classic yet industrially critical problem—estimating object poses for tasks like robotic grasping. By introducing a differentiable, coarse-to-fine refinement pipeline, her method achieves robust matching even under challenging conditions, earning 17 citations shortly after publication. This work directly addresses the limitations of traditional approaches when template and source images differ significantly. Yi also contributes to autonomous exploration with her paper "THP: Tensor-field-driven hierarchical path planning for autonomous scene exploration with depth sensors," which proposes a novel tensor field-based framework to efficiently navigate unknown 3D environments using only depth data. This innovation enhances a robot’s ability to encode and utilize spatial information despite a limited field of view. With a focus on practical, industry-relevant solutions, Yi’s research is poised to impact manufacturing automation and autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2