MengyangPu/RINDNet

RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depth, in ICCV 2021 (oral)

34
/ 100
Emerging

This project helps computer vision researchers and practitioners accurately detect various types of edges in images. It takes standard image files as input and outputs detailed maps highlighting different edge categories: those caused by changes in surface reflectance, illumination, surface normal, and depth. This tool is designed for anyone working on advanced image analysis, scene understanding, or 3D reconstruction who needs a precise understanding of object boundaries and surface properties.

126 stars. No commits in the last 6 months.

Use this if you need to identify and categorize specific types of edges in images, beyond just generic boundary detection.

Not ideal if you only need basic object detection or segmentation, as this tool focuses specifically on the nuanced classification of edge types.

image-analysis computer-vision-research scene-understanding 3d-reconstruction robotics
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

126

Forks

18

Language

Python

License

Last pushed

Sep 28, 2022

Commits (30d)

0

Get this data via API

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

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