UkcheolShin/ThermalSfMLearner-MS
Official implementation of the paper "Self-supervised Depth and Ego-motion Estimation for Monocular Thermal Video using Multi-spectral Consistency Loss"
This project helps operations engineers, security personnel, or emergency responders analyze thermal video footage. It takes a single stream of thermal video and, without needing additional sensors or prior mapping, estimates how far away objects are and how the camera itself is moving. This allows for detailed scene understanding in challenging environments like nighttime or smoke.
No commits in the last 6 months.
Use this if you need to understand depth and camera movement from monocular thermal video, especially when traditional visual methods are hindered by low light or obscured visibility.
Not ideal if your primary data source is standard visible light video, or if you require real-time processing on embedded systems without significant computational resources.
Stars
40
Forks
7
Language
Python
License
GPL-3.0
Category
Last pushed
Jul 19, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/UkcheolShin/ThermalSfMLearner-MS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cake-lab/HybridDepth
Official implementation for HybridDepth Model [WACV 2025, ISMAR 2024]
ialhashim/DenseDepth
High Quality Monocular Depth Estimation via Transfer Learning
soubhiksanyal/RingNet
Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision
nianticlabs/monodepth2
[ICCV 2019] Monocular depth estimation from a single image
tinghuiz/SfMLearner
An unsupervised learning framework for depth and ego-motion estimation from monocular videos