Fulong Xu
Papers
1
Total Citations
10
H-Index
1
About
Fulong Xu is a rising researcher in computer vision, with a primary focus on self-supervised monocular depth estimation—a cost-effective alternative to laser-based sensing that uses only a single camera to infer dense depth maps. His most cited work, "Joint Soft–Hard Attention for Self-Supervised Monocular Depth Estimation" (2021, 10 citations), addresses a critical challenge in the field: improving estimation accuracy without sacrificing the advantages of self-supervision. By introducing a novel joint soft–hard attention mechanism, Xu’s method enhances the model’s ability to focus on both fine-grained details and global structural cues, leading to more robust depth predictions in complex scenes. This contribution is particularly notable for its potential to advance autonomous driving, robotics, and augmented reality applications, where reliable depth perception is essential. While still early in his career, Xu’s work demonstrates a clear commitment to bridging the gap between self-supervised learning and practical deployment, earning recognition among peers for its innovative approach to a fundamental problem in 3D vision.
Research Focus
Key Achievements
Top Papers
- 1Joint Soft–Hard Attention for Self-Supervised Monocular Depth Estimation10 citations · 2021