lihaoliu-cambridge/scotch-and-soda

[CVPR'23] Code for "SCOTCH and SODA: A Transformer Video Shadow Detection Framework".

31
/ 100
Emerging

This project helps computer vision researchers and developers identify and segment shadows in video footage. It takes raw video data as input and produces pixel-level masks that precisely outline shadow regions. This is useful for anyone working on video analysis tasks where shadows might interfere with object detection or scene understanding.

No commits in the last 6 months.

Use this if you need to accurately detect and remove shadows from video frames as part of a larger computer vision pipeline or research project.

Not ideal if you are looking for an out-of-the-box application for end-users rather than a research framework requiring technical setup and expertise.

video-analysis computer-vision image-segmentation scene-understanding research-tool
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 17 / 25

How are scores calculated?

Stars

21

Forks

8

Language

Python

License

Last pushed

Nov 05, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/lihaoliu-cambridge/scotch-and-soda"

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