Skip to main content

Background Eraser

Background Eraser allows the user to remove the background and extract the foreground. The output image is a PNG with Alpha channel containing the transparency value of the background.

This transformation supports png, jpeg, jpg, webp, cr2, nef, rw2, dng, orf, raw, heic, heif, avif, tiff and tif type of files.


Params

Industry Type (i)

The usage type for the output image.

Available values are general, ecommerce, car, and human. The default is general.

general

The general industry type can be applied to all types of images.

ecommerce

The ecommerce industry type should be applied to images from e-commerce websites or any e-commerce product. It is specially trained and tuned for e-commerce images like apparel, shoes etc.

car

The car industry type should be applied to images that contain cars. This will erase not just the backdrop from car images, but also the background viewed through the car windows.

note

The car industry type is in preview mode.

human

For certain unnatural camera angles (e.g., like those in overhead photobooths), the user may need to specify specifically that it is the human region in the image that needs to be extracted as the foreground. In such scenarios ‘human’ Industry type should be selected.

Refine Output

True

Foregrounds are extracted with better boundary details, however it may take ever so slightly longer processing time.

False

No boundary refinement is performed. The boundary quality might decrease slightly, however it is going to give faster results.

Shadow (shadow)

Adds shadow to the output image. shadow is an alias for this parameter.

Only usable when images are cars. The default is false.

Output

Format: png
Content: A 4-channel png image with the alpha channel present.

Transform and enhance your images using our powerful AI technology. Organize your images in more efficient manner and our extensible APIs enables seamless integration with your system unleashing the power of our platform. Join the large community of users who use PixelBin to transform their image libraries and achieve excellent performance

Is this page useful?