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...
Saved in:
Main Author: | Nallapati, Nikhil |
---|---|
Other Authors: | Lam Siew Kei |
Format: | Thesis-Master by Research |
Language: | English |
Published: |
Nanyang Technological University
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/180792 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
Similar Items
-
Semantic-discriminative mixup for generalizable sensor-based cross-domain activity recognition
by: Lu, Wang, et al.
Published: (2023) -
Using stereo visual geometry to aid in robotic motion and navigation
by: Sivaguru, Esshwar
Published: (2024) -
The generalizability of leadership across activity domains and time periods
by: Park, K.W., et al.
Published: (2014) -
Event-based stereo matching using semiglobal matching
by: Xie, Z, et al.
Published: (2020) -
Building generalizable deep learning solutions for mobile sensing
by: Xu, Huatao
Published: (2024)