Zhaoxing Zhang

Huazhong University of Science and Technology

Papers

Total Citations

H-Index

About

Zhaoxing Zhang is a leading researcher in computer vision, with a primary focus on stereo matching—a critical technology for depth perception in autonomous systems and robotics. His most impactful contribution is the development of the **IGEV++ architecture** (Iterative Multi-Range Geometry Encoding Volumes), a novel deep network that tackles the persistent challenge of matching ambiguities in ill-posed regions and large disparities. By introducing multi-range geometry encoding volumes, Zhang’s work significantly improves the accuracy and robustness of stereo depth estimation, even under difficult conditions. His 2025 paper on IGEV++ has already garnered **37 citations**, underscoring its rapid influence and adoption in the field. This work builds on his earlier 2024 publication, which laid the foundational concepts. Zhang’s innovations are not only advancing academic research but also have direct implications for real-world applications in autonomous driving, 3D reconstruction, and robotic navigation. His contributions represent a meaningful step forward in making stereo vision systems more reliable and precise, positioning him as a rising authority in geometric deep learning and computer vision.