Chrisding/seal
Code for Simultaneous Edge Alignment and Learning (SEAL)
This project helps computer vision researchers accurately identify and outline objects in images, even when initial labels are imperfect. It takes raw image data and potentially noisy object boundary labels, then produces precise, thin object outlines without needing extra clean-up steps. This is designed for researchers working on advanced image analysis and autonomous systems.
123 stars. No commits in the last 6 months.
Use this if you need to extract crisp, high-quality object boundaries from images, especially when dealing with large datasets and noisy or imprecise initial labels.
Not ideal if you're looking for a simple, off-the-shelf tool for basic image segmentation without deep learning research involvement.
Stars
123
Forks
21
Language
C++
License
MIT
Category
Last pushed
Nov 13, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Chrisding/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,...