alexklwong/learning-topology-synthetic-data
Tensorflow implementation of Learning Topology from Synthetic Data for Unsupervised Depth Completion (RAL 2021 & ICRA 2021)
This project helps robotics engineers and computer vision researchers generate highly accurate, dense 3D depth maps from standard camera images and sparse depth sensor readings. It takes an RGB image and a sparse depth map (from lidar or SfM) as input. The output is a refined, dense depth map that accurately represents the 3D scene, which is crucial for autonomous navigation and 3D reconstruction.
No commits in the last 6 months.
Use this if you need to create detailed 3D scene geometry for robotics, autonomous vehicles, or 3D mapping applications, especially when working with limited sparse depth data.
Not ideal if you require real-time processing speeds significantly faster than 15 ms/frame or are looking for a solution that avoids using synthetic data during training.
Stars
36
Forks
6
Language
Python
License
—
Category
Last pushed
Jul 23, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/alexklwong/learning-topology-synthetic-data"
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