Qizeng Jia

Huazhong University of Science and Technology

Papers

Total Citations

H-Index

About

Qizeng Jia is a researcher in computer vision and robotics, with a primary focus on monocular depth estimation and geometric deep learning. His most cited work, "DENAO: Monocular Depth Estimation Network with Auxiliary Optical Flow" (2020, 17 citations), introduces a novel convolutional neural network that leverages optical flow and epipolar geometry to improve depth estimation from multi-view images captured by a localized monocular camera. This contribution addresses a fundamental challenge in 3D scene understanding, offering a more robust approach to inferring depth from limited visual input. Jia’s work bridges the gap between traditional geometric methods and modern learning-based techniques, demonstrating how auxiliary tasks like optical flow can enhance spatial reasoning in neural networks. While his citation count reflects a growing interest in his methodology, his research holds particular significance for applications in autonomous navigation, augmented reality, and robotic perception. By integrating geometric constraints with deep learning, Jia has provided a practical framework that advances the reliability of monocular depth estimation, making his work a valuable reference for students and researchers exploring efficient, geometry-aware vision systems.