Max Robotics — Global Service Robot Directory + US Certification

About

Jiguang Zhang is a researcher advancing the frontiers of 3D computer vision and robotic perception. His work centers on multimodal representation learning, 3D scene understanding, and robust object manipulation in unstructured environments. Zhang’s most cited paper, “MRFTrans: Multimodal Representation Fusion Transformer for monocular 3D semantic scene completion” (2024, 24 citations), introduces a novel transformer architecture that fuses diverse sensory data to reconstruct complete 3D scenes from a single image, a critical capability for autonomous navigation and augmented reality. He also made significant contributions to robotic grasping with “Visual Reconstruction and Localization-Based Robust Robotic 6-DoF Grasping in the Wild” (2021, 6 citations), which enables manipulators to perform complex, six-degree-of-freedom grasps in unstructured settings—overcoming the limitations of traditional industrial robots restricted to simple top-down motions. Additionally, Zhang has explored 6D pose estimation through “C2Fi-NeRF: Coarse to fine inversion NeRF for 6D pose estimation” (2024, 3 citations) and developed methods for “Slicing components guided indoor objects vectorized modeling from unilateral point cloud data” (2022, 3 citations). His research, bridging perception and action, is paving the way for more intelligent, adaptable robots capable of operating in the wild.