Chia-Chun Cheng

Papers

Total Citations

H-Index

About

Chia-Chun Cheng is a researcher whose work centers on advancing computer vision, particularly in the domain of 3D object detection from monocular imagery. His most cited paper, "3D Object Detection from Consecutive Monocular Images" (2021), tackles the challenging problem of inferring three-dimensional spatial information from standard two-dimensional camera feeds—a critical capability for autonomous driving and robotics. By leveraging temporal cues from consecutive frames, Cheng’s approach improves depth estimation and object localization without relying on expensive LiDAR sensors, making 3D perception more accessible and cost-effective. Though his citation count is currently modest, his contributions are foundational to a rapidly growing field, where monocular methods are increasingly vital for real-world deployment. Cheng’s work demonstrates a clear focus on bridging the gap between theoretical computer vision algorithms and practical, sensor-limited applications. As the demand for efficient, scalable perception systems rises, his research is poised to gain significant traction, offering a promising pathway for students and engineers seeking to innovate in autonomous systems and visual understanding.