p-ranav/merged_depth
Monocular Depth Estimation - Weighted-average prediction from multiple pre-trained depth estimation models
This tool helps you accurately determine the distance of objects in an image from a single photograph, a task known as monocular depth estimation. You provide a standard 2D image, and it outputs a map showing the absolute depth (distance in meters) for every pixel, along with a visual representation. This is useful for researchers and developers working in fields like robotics, augmented reality, or 3D scene reconstruction.
No commits in the last 6 months.
Use this if you need to extract precise, per-pixel depth information in meters from individual 2D images using a robust, combined approach.
Not ideal if you require real-time video processing or if your application specifically needs stereo vision or LiDAR data for depth sensing.
Stars
48
Forks
3
Language
Python
License
MIT
Category
Last pushed
Nov 03, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/p-ranav/merged_depth"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
vita-epfl/monoloco
A 3D vision library from 2D keypoints: monocular and stereo 3D detection for humans, social...
fangchangma/self-supervised-depth-completion
ICRA 2019 "Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and...
nburrus/stereodemo
Small Python utility to compare and visualize the output of various stereo depth estimation algorithms
JiawangBian/sc_depth_pl
SC-Depth (V1, V2, and V3) for Unsupervised Monocular Depth Estimation ...
wvangansbeke/Sparse-Depth-Completion
Predict dense depth maps from sparse and noisy LiDAR frames guided by RGB images. (Ranked 1st...