noelshin/PixelPick
[ICCVW'21 Best Paper Award] All you need are a few pixels: semantic segmentation with PixelPick
This project helps image annotators significantly speed up the creation of detailed pixel-level masks for image segmentation. Instead of outlining entire objects, you provide just a few key pixels for each object in an image. The system then generates a complete, high-quality segmentation mask based on these minimal inputs, drastically reducing the time and effort required for annotation.
No commits in the last 6 months.
Use this if you need to create precise pixel-level annotations for large image datasets but want to dramatically cut down on the manual labeling time.
Not ideal if your segmentation task requires extremely fine-grained, intricate annotations where human oversight of every pixel is absolutely critical.
Stars
67
Forks
12
Language
HTML
License
MIT
Category
Last pushed
Jun 18, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/noelshin/PixelPick"
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,...