NazirNayal8/RbA
Official code for RbA: Segmenting Unknown Regions Rejected by All (ICCV 2023)
This project helps computer vision engineers and researchers identify and segment 'unknown' or 'anomalous' regions within images, particularly in autonomous driving or surveillance contexts. It takes diverse image datasets as input and outputs precise segmentation masks that highlight unexpected objects or conditions. This tool is ideal for professionals building robust object detection and scene understanding systems.
No commits in the last 6 months.
Use this if you need to reliably detect and outline unusual or out-of-distribution elements in images that your standard object recognition models might miss.
Not ideal if you are looking for a pre-trained, off-the-shelf solution for common object detection tasks without the need for anomaly segmentation.
Stars
71
Forks
11
Language
Python
License
MIT
Category
Last pushed
Jan 10, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/NazirNayal8/RbA"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
JonasSchult/Mask3D
Mask3D predicts accurate 3D semantic instances achieving state-of-the-art on ScanNet,...
nsavinov/semantic3dnet
Point cloud semantic segmentation via Deep 3D Convolutional Neural Network
PRBonn/LiDAR-MOS
(LMNet) Moving Object Segmentation in 3D LiDAR Data: A Learning-based Approach Exploiting...
yanx27/2DPASS
2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds (ECCV 2022) :fire:
ctu-vras/traversability_estimation
Semantic Segmentation of Images and Point Clouds for Traversability Estimation