Yuqi Song

Papers

Total Citations

H-Index

About

Yuqi Song is a computer vision researcher whose work centers on depth estimation, 3D scene understanding, and perception systems for autonomous and robotic applications. Song's most recognized contribution, "Depth Monocular Estimation with Attention-based Encoder-Decoder Network from Single Image" (2022), addresses one of the fundamental challenges in autonomous driving and robotics: accurately recovering depth information from a single camera without relying on expensive hardware such as LiDAR or RADAR. By leveraging attention mechanisms within an encoder-decoder architecture, Song's approach demonstrates how deep learning can extract rich spatial information from monocular imagery, offering a computationally efficient alternative to sensor-heavy pipelines. This work, which has garnered 10 citations since its publication, reflects a growing research momentum in resource-constrained perception — a critical need as autonomous systems are deployed in real-world dynamic environments. Song's research sits at the intersection of computer vision and practical robotics engineering, contributing meaningful progress toward making depth perception more accessible, scalable, and responsive. For students and researchers exploring monocular depth estimation or embedded vision systems, Song's work represents a valuable entry point into attention-driven scene understanding.