robustsam/RobustSAM
RobustSAM: Segment Anything Robustly on Degraded Images (CVPR 2024 Highlight)
RobustSAM helps anyone working with images to accurately outline specific objects, even when the pictures are blurry, hazy, low-light, or have other quality issues. You provide it with a degraded image and some basic prompts (like a box around an object or a point on it), and it outputs a precise segmentation mask of the object. This is ideal for professionals like image analysts, quality control inspectors, or researchers who need reliable object isolation from imperfect visual data.
364 stars. No commits in the last 6 months.
Use this if you need to precisely segment objects in real-world images that are often affected by common degradations such as blur, haze, rain, or low light, and traditional segmentation tools struggle.
Not ideal if your images are consistently of very high quality and you don't encounter issues with visual degradation, as simpler segmentation models might suffice.
Stars
364
Forks
33
Language
Python
License
MIT
Category
Last pushed
Aug 31, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/robustsam/RobustSAM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
uber-research/UPSNet
UPSNet: A Unified Panoptic Segmentation Network
augmentedstartups/AS-One
Easy & Modular Computer Vision Detectors, Trackers & SAM - Run YOLOv9,v8,v7,v6,v5,R,X in under...
xuebinqin/U-2-Net
The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with...
shreyas-bk/u2netdemo
Demonstration using Google Colab to show how U-2-NET can be used for Background Removal,...
AIDajiangtang/Segment-Anything-CSharp
segment anything（SAM） WPF客户端