Su Inn Park

Papers

Total Citations

H-Index

About

Su Inn Park is a rising researcher in efficient computer vision, with a focus on depth estimation and transformer-based architectures. Her most-cited work, "Depth Estimation with Simplified Transformer" (2022, 11 citations), tackles a critical challenge in deploying state-of-the-art vision models: balancing accuracy with the low latency required for real-world applications. By streamlining complex transformer designs, Park’s research directly addresses the computational bottlenecks that hinder deployment in latency-critical systems, such as autonomous navigation or augmented reality. This contribution is particularly notable for its practical impact, offering a pathway to bring high-performance dense prediction tasks—like depth estimation—into resource-constrained environments. Park’s work sits at the intersection of model efficiency and advanced vision techniques, signaling her as a key voice in making cutting-edge AI more accessible and deployable. As her citation count grows, her focus on simplifying powerful yet cumbersome models promises to influence both academic research and industrial applications, marking her as a researcher to watch in the evolving landscape of efficient deep learning.