Papers
2
Total Citations
13
H-Index
1
About
Xiuju Gao is a rising researcher in the field of computer vision, with a focused expertise in monocular 3D object detection and depth estimation. Her most notable contribution is the development of MonoSAID, a novel framework for monocular 3D object detection that introduces scene-level adaptive instance depth estimation. This work, published in 2023 and garnering 12 citations, addresses a critical challenge in autonomous driving and robotics: accurately inferring 3D spatial information from a single 2D image. By dynamically adjusting depth predictions based on scene context, MonoSAID improves detection reliability in complex environments. Gao further advances the field with LightNet, a lightweight monocular depth estimation model optimized for high-level guidance and channel re-alignment, presented at ChinaMM in 2025. Her research emphasizes efficiency and practicality, aiming to deploy sophisticated 3D perception on resource-constrained platforms. As an emerging scholar, Gao’s work bridges the gap between algorithmic accuracy and real-world applicability, making her a promising voice in the next generation of computer vision researchers.
Research Focus
Key Achievements
Top Papers
- 1
- 2