Yiran Geng

Papers

Total Citations

H-Index

About

Yiran Geng is an emerging researcher at the intersection of computer vision and robotics, with a particular focus on robotic manipulation and visual perception. Their most notable work, "RGBManip: Monocular Image-based Robotic Manipulation through Active Object Pose Estimation" (2024), addresses one of the fundamental challenges in autonomous robotics: enabling robots to accurately perceive and interact with objects in complex, dynamic environments using only monocular RGB images. This contribution is significant because it bridges the gap between accessible, single-camera visual inputs and the precise pose estimation required for reliable robotic manipulation — reducing dependence on more expensive or complex sensor modalities like depth cameras or point-cloud systems. With 13 citations already accumulated in a short timeframe, Geng's work is gaining meaningful traction within the robotics and computer vision communities. The research reflects a broader commitment to making robotic systems more practical and deployable in real-world settings by leveraging cost-effective sensing approaches. As autonomous manipulation continues to grow in importance across industrial and service robotics applications, Geng's contributions position them as a promising voice in developing more perceptually intelligent and adaptable robotic systems.