About
Contact & Profiles
A5111217793
Research Areas
- Advanced Vision and Imaging
- Image Processing Techniques and Applications
- Optical measurement and interference techniques
Monocular depth estimation, enabled by self-supervised learning, is a key technique for 3D perception in computer vision. However, it faces significant challenges real-world scenarios, which encompass adverse weather variations, motion blur, as well scenes with poor lighting conditions at night. Our research reveals that we can divide monocular estimation into three sub-problems: structure consistency, local texture disambiguation, and semantic-structural correlation. approach tackles the...
10.48550/arxiv.2410.06982
preprint
EN
arXiv (Cornell University)
2024-10-09
Coming Soon ...