Max Robotics — Global Service Robot Directory + US Certification

About

Wenjun Shi is a leading researcher in 3D computer vision and robotic perception, with a focus on semantic mapping, scene understanding, and object pose estimation. Their work bridges the gap between raw sensor data and actionable spatial intelligence for autonomous systems. Shi’s most cited paper, “RGB-D Semantic Segmentation and Label-Oriented Voxelgrid Fusion for Accurate 3D Semantic Mapping” (2021, 67 citations), introduces a novel methodology for constructing detailed 3D semantic maps from RGB-D scans, a critical capability for task-driven robots. They further advanced dynamic environment handling in “Dynamic Obstacles Rejection for 3D Map Simultaneous Updating” (2018, 14 citations), proposing an efficient method to eliminate spurious trails from moving objects. Shi’s contributions extend to bionic vision with “Multilevel Cross-Aware RGBD Indoor Semantic Segmentation for Bionic Binocular Robot” (2020, 13 citations), which mimics human visual perception for improved scene understanding. More recently, in “SD-Pose: Structural Discrepancy Aware Category-Level 6D Object Pose Estimation” (2023, 8 citations), they tackle the challenge of estimating pose and size for unseen object instances, essential for robot grasping and augmented reality. With a growing body of work accumulating over 100 citations, Wenjun Shi is shaping the future of intelligent robotic interaction with complex, dynamic environments.