Lili Ju
Papers
1
Total Citations
28
H-Index
1
About
Lili Ju is a leading researcher in computer vision and machine learning, with a primary focus on 3D scene understanding, depth estimation, and generative models. Her major contributions lie in advancing monocular depth estimation—a critical challenge for autonomous driving and robot navigation—by developing novel frameworks that learn spatial correspondence without relying on precise camera-pose information. In her highly cited 2019 work, "Spatial Correspondence With Generative Adversarial Network: Learning Depth From Monocular Videos," Ju introduced a generative adversarial network (GAN) approach that robustly estimates depth from video sequences, mitigating errors from camera-pose estimation. This paper has garnered 28 citations, reflecting its impact on the field. Beyond this, Ju’s research spans image synthesis, video analysis, and deep learning architectures, consistently pushing the boundaries of unsupervised and self-supervised learning. Her work is recognized for its practical relevance, offering solutions that enhance the reliability of perception systems in real-world applications. Ju’s contributions have made her a respected voice in the computer vision community, inspiring further exploration into robust, data-efficient depth estimation techniques.
Research Focus
Key Achievements
Top Papers
- 1