Chaewon Park

Papers

Total Citations

H-Index

About

Chaewon Park is a researcher advancing the field of computer vision, with a primary focus on monocular depth estimation for robotics and autonomous driving. Her most-cited work, "EdgeConv with Attention Module for Monocular Depth Estimation" (2022, 25 citations), tackles a critical challenge: predicting accurate 3D structural information from a single image under difficult conditions, such as extreme lighting or complex surface textures. Park’s key contribution lies in integrating an EdgeConv layer with an attention mechanism, enabling the model to better capture fine-grained geometric details and suppress noise, thereby producing more reliable depth maps. This innovation directly addresses the limitations of traditional methods in real-world scenarios, where robust perception is essential for safe navigation. Beyond this paper, Park’s research continues to explore how attention-based architectures can enhance spatial understanding in vision systems. Her work has already garnered recognition for its practical relevance, bridging the gap between algorithmic efficiency and deployment in safety-critical applications. For students and researchers interested in deep learning for 3D scene understanding, Park’s contributions offer a compelling example of how targeted architectural improvements can yield significant performance gains.