Uncertainty guided ranking loss for enhanced domain generalizable stereo-matching
Stereo-matching is a fundamental technique for accurately estimating scene depth in numerous computer vision applications. However, prevailing deep learning-based stereo-matching networks frequently encounter challenges regarding generalization across different domains. Recent research endeavors hav...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Master by Research |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/180792 |