pxl-th/Monodepth2.jl
Self-supervised monocular depth estimation
This tool helps computer vision researchers and robotics engineers convert standard 2D images into detailed depth maps, which show the distance of objects from the camera. You feed it a single image or a sequence of images, and it outputs a disparity map highlighting depth, useful for tasks like scene understanding or autonomous navigation. This is ideal for those working with visual data where depth information is critical but specialized sensors aren't available.
No commits in the last 6 months.
Use this if you need to estimate the depth of objects in a scene from standard camera images without using stereo cameras or LiDAR.
Not ideal if you require highly precise, absolute depth measurements for safety-critical applications, as monocular depth estimation has inherent limitations.
Stars
13
Forks
2
Language
Julia
License
—
Category
Last pushed
Feb 07, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pxl-th/Monodepth2.jl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
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