HarborYuan/PolyphonicFormer

[ECCV 2022] 🎵PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation

25
/ 100
Experimental

This project helps self-driving car engineers and robotics researchers analyze sensor data by precisely identifying and categorizing every object in a video stream while also estimating its distance from the camera. It takes raw video and depth sensor data as input and outputs a detailed, segmented view of the scene, with each object (like cars, pedestrians, or road surfaces) clearly delineated and assigned a depth value. This is used by engineers developing autonomous navigation systems.

No commits in the last 6 months.

Use this if you need to understand both what objects are present in a video scene and how far away they are, for applications like autonomous driving or advanced robotics.

Not ideal if your primary goal is simple object detection without needing fine-grained segmentation or depth information, or if you only work with still images.

autonomous-driving robotics scene-understanding computer-vision depth-perception
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 9 / 25

How are scores calculated?

Stars

56

Forks

4

Language

Python

License

Last pushed

Dec 22, 2022

Commits (30d)

0

Get this data via API

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

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