Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,79 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
RemoveG is a browser-based AI image background remover designed to process images locally on the user's device.
|
| 3 |
+
|
| 4 |
+
๐ Website
|
| 5 |
+
|
| 6 |
+
https://www.removeg.io/
|
| 7 |
+
|
| 8 |
+
โจ Features
|
| 9 |
+
Automatic image background removal
|
| 10 |
+
Client-side image processing
|
| 11 |
+
WebAssembly and WebGPU acceleration
|
| 12 |
+
Support for PNG, JPG, JPEG, and WebP images
|
| 13 |
+
Designed for fast browser-based inference
|
| 14 |
+
No account required for basic usage
|
| 15 |
+
Privacy-focused image processing
|
| 16 |
+
๐ง Model
|
| 17 |
+
|
| 18 |
+
RemoveG uses the IS-Net / InSPyReNet approach for salient object detection and foreground extraction.
|
| 19 |
+
|
| 20 |
+
The model can be useful for:
|
| 21 |
+
|
| 22 |
+
Product photography
|
| 23 |
+
Portrait images
|
| 24 |
+
E-commerce images
|
| 25 |
+
Logos and graphics
|
| 26 |
+
Signatures
|
| 27 |
+
General foreground extraction
|
| 28 |
+
โก Browser Inference
|
| 29 |
+
|
| 30 |
+
The RemoveG web application uses ONNX Runtime Web to run machine-learning inference directly in the browser.
|
| 31 |
+
|
| 32 |
+
Depending on browser and hardware support, inference can utilize:
|
| 33 |
+
|
| 34 |
+
WebGPU
|
| 35 |
+
WebAssembly
|
| 36 |
+
Multi-threaded WebAssembly
|
| 37 |
+
|
| 38 |
+
This approach allows image processing without requiring a traditional remote image-processing API.
|
| 39 |
+
|
| 40 |
+
๐ Privacy
|
| 41 |
+
|
| 42 |
+
RemoveG is designed with privacy in mind. Image processing is performed on the user's device through browser-based inference.
|
| 43 |
+
|
| 44 |
+
Learn more at:
|
| 45 |
+
|
| 46 |
+
https://www.removeg.io/
|
| 47 |
+
|
| 48 |
+
๐ ๏ธ Technology
|
| 49 |
+
Component Technology
|
| 50 |
+
Background Removal IS-Net / InSPyReNet
|
| 51 |
+
Model Runtime ONNX Runtime Web
|
| 52 |
+
GPU Acceleration WebGPU
|
| 53 |
+
CPU Runtime WebAssembly
|
| 54 |
+
Processing Client-side
|
| 55 |
+
Output Formats PNG, JPG, JPEG, WebP
|
| 56 |
+
๐ Use Cases
|
| 57 |
+
E-commerce
|
| 58 |
+
|
| 59 |
+
Remove backgrounds from product images to create clean product photography.
|
| 60 |
+
|
| 61 |
+
Portraits
|
| 62 |
+
|
| 63 |
+
Create transparent-background profile pictures, headshots, and other portraits.
|
| 64 |
+
|
| 65 |
+
Graphic Design
|
| 66 |
+
|
| 67 |
+
Extract foreground objects for thumbnails, advertisements, presentations, and social media graphics.
|
| 68 |
+
|
| 69 |
+
๐ Learn More
|
| 70 |
+
|
| 71 |
+
Visit RemoveG.io to try the browser-based image background remover.
|
| 72 |
+
|
| 73 |
+
โ ๏ธ Model Information
|
| 74 |
+
|
| 75 |
+
This project uses the IS-Net / InSPyReNet approach for image salient-object detection. Please refer to the original model implementation and its associated license for details about the underlying model.
|
| 76 |
+
|
| 77 |
+
๐ Keywords
|
| 78 |
+
|
| 79 |
+
background-removal image-segmentation IS-Net InSPyReNet ONNX ONNX-Runtime-Web WebGPU WebAssembly image-processing foreground-extraction browser-AI
|