Arlo0o/HTCL

[ECCV 2024, IEEE TPAMI] Official PyTorch Implementation of HTCL : Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion

44
/ 100
Emerging

This project helps self-driving car engineers and robotics researchers by converting a stream of 2D camera images into a detailed 3D map of the environment, identifying objects and open spaces. It takes video feeds from vehicle cameras and outputs a rich, semantically labeled 3D occupancy grid, which is crucial for navigation and obstacle avoidance. The main users are perception system developers for autonomous vehicles and robotics.

Use this if you need to generate highly accurate 3D semantic maps of dynamic outdoor environments solely from camera data, outperforming even some LiDAR-based methods.

Not ideal if your application does not involve camera-based 3D scene reconstruction for autonomous navigation or if you primarily work with static environments.

autonomous-driving robotics 3D-reconstruction scene-understanding perception-systems
No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

51

Forks

5

Language

Python

License

Apache-2.0

Last pushed

Feb 27, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Arlo0o/HTCL"

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