jytime/Deep-SfM-Revisited

[CVPR 2021] Deep Two-View Structure-from-Motion Revisited

37
/ 100
Emerging

This project helps computer vision researchers and robotics engineers convert pairs of images into a 3D understanding of the scene. By inputting two images of a scene, it can output essential matrices, depth maps, and camera poses, enabling 3D reconstruction and motion estimation. It is ideal for those working with autonomous navigation or 3D scene understanding from image data.

190 stars. No commits in the last 6 months.

Use this if you need to determine the 3D structure and camera movement from two uncalibrated images, especially for autonomous driving or robotics applications.

Not ideal if you are looking for a plug-and-play solution without expertise in deep learning, PyTorch, or large-scale computer vision datasets like KITTI.

3D-reconstruction robotics-navigation autonomous-driving computer-vision depth-estimation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

190

Forks

13

Language

Python

License

MIT

Last pushed

Apr 23, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/jytime/Deep-SfM-Revisited"

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