NeurAI-Lab/MT-SfMLearner

Official code for 'Transformers in Unsupervised Structure-from-Motion' and 'Transformers in Self-Supervised Monocular Depth Estimation with Unknown Camera Intrinsics'

31
/ 100
Emerging

This project helps computer vision researchers analyze video sequences to understand the 3D structure of scenes and objects. It takes video footage as input and outputs detailed depth maps for each frame, even if the camera's internal settings are unknown. This is ideal for researchers in robotics, autonomous driving, or 3D reconstruction who need to extract spatial information from videos.

No commits in the last 6 months.

Use this if you need to determine the precise distance of objects from a camera in video footage without needing to calibrate the camera.

Not ideal if you require real-time processing on embedded devices or have static images rather than video sequences for analysis.

3D reconstruction robotics vision autonomous vehicle perception depth estimation computer vision research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

14

Forks

2

Language

Python

License

MIT

Last pushed

Nov 12, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/NeurAI-Lab/MT-SfMLearner"

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