antocad/FocusOnDepth
A Monocular depth-estimation for in-the-wild AutoFocus application.
This project helps photographers and videographers enhance auto-focus capabilities in challenging, uncontrolled environments by estimating the depth of objects in a scene. You provide a standard image or video frame, and it generates a depth map (showing how far away objects are) and, optionally, a segmentation mask (identifying specific objects like people). This is ideal for anyone working with 'in-the-wild' imagery where precise focus is critical, such as portrait photographers, documentary filmmakers, or even security professionals.
155 stars. No commits in the last 6 months.
Use this if you need to automatically determine the distance of objects in a single image or video frame for improved auto-focus or scene understanding, especially when dealing with unpredictable real-world conditions.
Not ideal if you already have stereo vision or LiDAR data, or if you need highly precise, sub-millimeter depth measurements for industrial applications.
Stars
155
Forks
32
Language
Python
License
MIT
Category
Last pushed
Jul 18, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/antocad/FocusOnDepth"
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...