An extensive evaluation and comparison of 28 state-of-the-art superpixel algorithms on 5 datasets.
-
Updated
Jan 6, 2024 - C++
An extensive evaluation and comparison of 28 state-of-the-art superpixel algorithms on 5 datasets.
Library containing 7 state-of-the-art superpixel algorithms with a total of 9 implementations used for evaluation purposes in [1] utilizing an extended version of the Berkeley Segmentation Benchmark.
20x Real-time superpixel SLIC Implementation with CPU
Extended version of the Berkeley Segmentation Benchmark [1] used for evaluation in [2].
Implementation of the superpixel algorithm called SEEDS [1].
Implementation of efficient graph-based image segmentation as proposed by Felzenswalb and Huttenlocher [1] that can be used to generate oversegmentations.
Learning Superpixels with Segmentation-Aware Affinity Loss
Superpixels segmentation algorithms with QT and OpenCV, with a nice GUI to colorize the cells
Invariant Superpixel Features for Object Detection
Example of using VLFeat's SLIC implementation from C++.
Image segmentation method for the generation of superpixels called waterpixels which follow an image contours.
HERS Superpixels: Deep Affinity Learning for Hierarchical Entropy Rate Segmentation
Real-time Superpixel Segmentation by DBSCAN Clustering Algorithm (TIP16)
Codes to compute Turbopixels/Turbovoxels and other related tools
Implementation of simplified version of SLIC Superpixels algorithm
Superpixel and Supervoxel computing
Task at UIIP NASB
Add a description, image, and links to the superpixels topic page so that developers can more easily learn about it.
To associate your repository with the superpixels topic, visit your repo's landing page and select "manage topics."