AyeCalc
All tools
Image tools

Free Background Remover Online

Choose a JPEG, PNG, or WebP image and create a transparent PNG with browser-based foreground segmentation. The image is processed in a dedicated browser worker, while the model and runtime files are downloaded on first use and cached by the browser when available.

Local image processingTransparent PNG outputNo account
Browser-based image segmentation

Remove an image background

Image stays local
Drop an image here

JPEG, PNG, or WebP · up to 50 MB and 25 megapixels

Choose a JPEG, PNG, or WebP image to begin.

First use downloads an approximately 44 MB quantized model plus browser runtime files. The browser may cache them for later use.

Core formulatransparent pixel = source pixel × foreground alpha mask

The segmentation model estimates a foreground mask from 0 (transparent) to 1 (opaque) for each pixel.

01
Method

How the background remover works

The browser decodes the selected image, resizes a working copy for the segmentation model, and predicts which pixels belong to the main foreground subject. That mask is resized to the original dimensions and applied as an alpha channel, preserving the original RGB pixels in a transparent PNG.

Formulatransparent pixel = source pixel × foreground alpha mask

The segmentation model estimates a foreground mask from 0 (transparent) to 1 (opaque) for each pixel.

02
Worked example

Remove the background from a product or portrait image

Select a supported image, start removal, and wait for the first-use model download and local processing. The preview displays transparency as a checkerboard. Downloading saves the original dimensions as a PNG with an alpha channel.

03
Output

Using the transparent PNG

Preserve the PNG alpha channel and provide accurate dimensions and alternative text when adding the result to a page.

HTML transparent image
<img src="subject-no-background.png" width="1200" height="800" alt="Product shown without its original background">
CSS preview surface
.transparent-preview {
  background-color: #fff;
  background-image:
    linear-gradient(45deg, #e5e7eb 25%, transparent 25%),
    linear-gradient(-45deg, #e5e7eb 25%, transparent 25%);
}
04
Practical guidance

Using the result accurately

Use a clearly defined foreground subject, adequate lighting, and visible separation between subject and background. Inspect hair, fur, glass, shadows, and similarly colored edges at full size before using the result in production.

Important limitation

Automatic segmentation can remove fine foreground detail or retain parts of a complex background. Processing speed depends on the device, browser, image dimensions, model cache, and available memory. The tool does not provide manual mask correction.

References: Hugging Face ONNX Community: ORMBG background-removal model.

Common questions

Background Remover FAQ

Answers about the method, assumptions, and practical use.

Does AyeCalc upload my selected image?

No. The selected image is passed to a worker inside your browser and is not intentionally uploaded to AyeCalc, Hugging Face, or jsDelivr. The browser separately downloads the model from Hugging Face and runtime files from jsDelivr on first use.

Why can the first background removal take longer?

The first run downloads the quantized segmentation model and browser runtime. Browsers can cache those files, so later runs may avoid downloading them again.

Which image formats are supported?

The uploader accepts JPEG, PNG, and WebP files up to 50 MB and 25 megapixels. Lower-memory devices can use a smaller pixel limit for stability. The result is downloaded as a transparent PNG.

Will every edge be removed perfectly?

No automatic model is perfect. Fine hair, fur, transparent objects, motion blur, low contrast, and complex scenes can produce inaccurate edges or missing foreground details.