SysCV/idisc

iDisc: Internal Discretization for Monocular Depth Estimation [CVPR 2023]

39
/ 100
Emerging

This project helps computer vision practitioners and researchers accurately estimate the depth of objects and surfaces in a scene using just a single image. It takes a standard color image as input and outputs a detailed depth map, showing how far away each part of the scene is. This is ideal for anyone working with 3D scene understanding from 2D photos.

293 stars. No commits in the last 6 months.

Use this if you need to determine the distance to objects in an environment, reconstruct 3D scenes, or enable autonomous navigation using only visual information from a single camera.

Not ideal if you require real-time processing on highly constrained embedded systems or have access to stereo cameras or LiDAR, which can provide direct depth measurements.

3D-scene-reconstruction autonomous-driving robotics-perception computer-vision depth-sensing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

293

Forks

21

Language

Python

License

Last pushed

Aug 14, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/SysCV/idisc"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.