Chih‐Yuan Yao

National Taiwan University of Science and Technology

Papers

Total Citations

H-Index

About

Chih-Yuan Yao is a researcher whose work sits at the intersection of computer vision and deep learning, with a particular focus on depth perception from limited visual data. His most cited contribution, “Single-Image Depth Inference Using Generative Adversarial Networks” (2019), tackles a fundamental challenge in perception: inferring accurate depth information from a single photograph. This capability is critical for enabling real-world applications such as robot grasping, obstacle avoidance, and autonomous navigation—technologies essential to the development of smart homes and smart cities. By leveraging generative adversarial networks, Yao’s work demonstrates how deep learning can overcome the traditional reliance on expensive depth sensors or multi-camera setups, making depth estimation more accessible and practical. With 10 citations, this paper has helped advance the field of monocular depth estimation, offering a pathway toward more intelligent and cost-effective perception systems. Yao’s research continues to explore how machines can interpret the three-dimensional world from two-dimensional inputs, contributing to the broader goal of building autonomous systems that see and understand their environment with greater efficiency and accuracy.