wctu/SEAL
Learning Superpixels with Segmentation-Aware Affinity Loss
This helps researchers in computer vision accurately outline distinct regions within images. You input an image, and it outputs a more refined, precise set of 'superpixels' — segmented areas that group similar pixels together, making subsequent image analysis tasks like object detection or tracking more effective. It is designed for computer vision scientists and machine learning engineers working on image understanding projects.
No commits in the last 6 months.
Use this if you need to improve the initial segmentation of images into meaningful, boundary-aligned superpixels before performing higher-level image analysis.
Not ideal if you are looking for a general-purpose image editing tool or a solution for semantic segmentation that directly labels objects.
Stars
97
Forks
14
Language
C++
License
—
Category
Last pushed
Apr 04, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/wctu/SEAL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
hkchengrex/CascadePSP
[CVPR 2020] CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global...
nv-tlabs/GSCNN
Gated-Shape CNN for Semantic Segmentation (ICCV 2019)
lim-anggun/FgSegNet
FgSegNet: Foreground Segmentation Network, Foreground Segmentation Using Convolutional Neural...
jiwoon-ahn/irn
Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations, CVPR 2019 (Oral)
suyukun666/UFO
Official PyTorch implementation of the “A Unified Transformer Framework for Co-Segmentation,...