prstrive/EPCDepth

[ICCV 2021] Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation

42
/ 100
Emerging

This project helps self-driving car engineers and robotics researchers create accurate 3D spatial awareness from standard camera images. It takes a single image from a moving vehicle's camera and estimates the distance of every pixel, producing a depth map (disparity map). This is particularly useful for tasks like obstacle detection and path planning in autonomous systems.

129 stars. No commits in the last 6 months.

Use this if you need to generate highly accurate depth information from single camera images for autonomous vehicles or robotic navigation, especially when dealing with complex scenes and occlusions.

Not ideal if you require real-time processing on embedded systems with limited computational resources, or if you primarily work with datasets other than KITTI or NYUv2 without extensive adaptation.

autonomous-driving robotics 3D-reconstruction computer-vision spatial-awareness
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

129

Forks

18

Language

Python

License

MIT

Last pushed

Oct 17, 2021

Commits (30d)

0

Get this data via API

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

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