OniroAI/MonoDepth-PyTorch
Unofficial implementation of Unsupervised Monocular Depth Estimation neural network MonoDepth in PyTorch
This tool helps researchers and engineers analyze single camera images to understand the 3D structure of a scene. It takes a single RGB image as input and produces a depth map, which shows the distance of objects from the camera. This is particularly useful for those working on autonomous navigation, robotics, or augmented reality applications.
554 stars. No commits in the last 6 months.
Use this if you need to estimate object distances and scene depth from standard camera images without needing a stereo camera setup or specialized sensors.
Not ideal if you require extremely precise, lidar-level depth measurements or if your application cannot tolerate occasional inaccuracies inherent in monocular depth estimation.
Stars
554
Forks
130
Language
Python
License
—
Category
Last pushed
Jan 02, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/OniroAI/MonoDepth-PyTorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
vita-epfl/monoloco
A 3D vision library from 2D keypoints: monocular and stereo 3D detection for humans, social...
nianticlabs/monodepth2
[ICCV 2019] Monocular depth estimation from a single image
cake-lab/HybridDepth
Official implementation for HybridDepth Model [WACV 2025, ISMAR 2024]
fangchangma/self-supervised-depth-completion
ICRA 2019 "Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and...
ialhashim/DenseDepth
High Quality Monocular Depth Estimation via Transfer Learning