TRI-ML/dd3d

Official PyTorch implementation of DD3D: Is Pseudo-Lidar needed for Monocular 3D Object detection? (ICCV 2021), Dennis Park*, Rares Ambrus*, Vitor Guizilini, Jie Li, and Adrien Gaidon.

47
/ 100
Emerging

This project helps self-driving car engineers and researchers detect and understand the 3D position of objects (like other cars, pedestrians, or cyclists) using only standard camera images. It takes raw camera footage as input and outputs precise 3D bounding boxes around detected objects, indicating their location and dimensions in the real world. This is useful for developing autonomous navigation systems that rely solely on visual input.

493 stars. No commits in the last 6 months.

Use this if you need to perform 3D object detection in real-world driving scenarios using only monocular camera data and are looking for a robust, research-backed solution.

Not ideal if your application doesn't involve automotive 3D object detection or if you require object detection from sensor inputs other than standard camera images.

autonomous-driving 3d-object-detection computer-vision robotics automotive-perception
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

493

Forks

74

Language

Python

License

MIT

Last pushed

Nov 29, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/TRI-ML/dd3d"

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