xuebinqin/DIS
This is the repo for our new project Highly Accurate Dichotomous Image Segmentation
This tool precisely separates a main subject from its background in images, even for complex or fine details like hair or fur. You provide an image, and it outputs a segmented image, essentially 'cutting out' the subject. Artists, graphic designers, marketing professionals, or anyone creating visuals can use this to quickly isolate elements for their creative projects.
2,514 stars. No commits in the last 6 months.
Use this if you need to extract objects from images with very high precision for tasks like image editing, graphic design, or creating visual assets.
Not ideal if you need a solution for video processing or real-time applications, as the current focus is on still image segmentation.
Stars
2,514
Forks
290
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Sep 23, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/xuebinqin/DIS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
juglab/EmbedSeg
Code Implementation for EmbedSeg, an Instance Segmentation Method for Microscopy Images
xuebinqin/U-2-Net
The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with...
augmentedstartups/AS-One
Easy & Modular Computer Vision Detectors, Trackers & SAM - Run YOLOv9,v8,v7,v6,v5,R,X in under...
uber-research/UPSNet
UPSNet: A Unified Panoptic Segmentation Network
shreyas-bk/u2netdemo
Demonstration using Google Colab to show how U-2-NET can be used for Background Removal,...