Remove Background Competitors Benchmark (Remove.bg, Clipdrop, SAM, Azure)

On this page you will find a comparison of our Remove Background API against some of our competitors.

If you want to compare two results in details, we recommend using this website: https://www.diffchecker.com/image-compare/

Result Comparison

Home Decoration Images

Furniture Images

Apparel Images

Food Images

Cosmetic Images

Jewelry Images

People Images

Industry Images

Reproducing the results

If you want to reproduce the results of this benchmark, here are the Python scripts that were used to generate the images.

Before running this code, please download the original images that you want to re-process, and place them in a directory called original-images.

import os
import requests
import concurrent.futures

API_KEY = "YOUR_PHOTOROOM_API_KEY"

def process_image(input_image_path, output_image_path):
    try:
        url = "https://sdk.photoroom.com/v1/segment"

        with open(input_image_path, 'rb') as image_file:
            files = { "image_file": image_file }

            headers = {
                "Accept": "image/png, application/json",
                "pr-background-removal-model-version": "2024-09-26",
                "x-api-key": API_KEY
            }

            response = requests.post(url, files=files, headers=headers)
            response.raise_for_status()

            with open(output_image_path, 'wb') as f:
                f.write(response.content)
                print(f"Image downloaded and saved to {output_image_path}")

    except requests.RequestException as e:
        print(f"Error: {str(e)} ({input_image_path})")
        return str(e)
    
def iterate_over_directory(directory_path, result_directory):
    with concurrent.futures.ThreadPoolExecutor(max_workers=16) as executor:
        for root, _, files in os.walk(directory_path):
            for file in files:
                if file.lower().endswith(('.png', '.jpg', '.jpeg', '.webp', '.heic')):
                    file_path = os.path.join(root, file)

                    result_file_name = os.path.splitext(os.path.basename(file_path))[0] + '.png'
                    result_file_directory = os.path.join(result_directory, os.path.basename(root))

                    if not os.path.exists(result_file_directory):
                        os.makedirs(result_file_directory)

                    result_path = os.path.join(result_file_directory, result_file_name)

                    if not os.path.exists(result_path): # don't re-process images 
                        executor.submit(process_image, file_path, result_path)    

if __name__ == "__main__":
    INPUT_DIRECTORY = "./original-images/"
    OUTPUT_DIRECTORY = "./result-photoroom/"

    if not os.path.exists(OUTPUT_DIRECTORY):
        os.makedirs(OUTPUT_DIRECTORY)

    iterate_over_directory(directory_path=INPUT_DIRECTORY, result_directory=OUTPUT_DIRECTORY)

Before running this code, please download the original images that you want to re-process, and place them in a directory called original-images.

import os
import requests

API_KEY = "YOUR_REMOVE_BG_API_KEY"

def process_image(input_image_path, output_image_path):
    try:
        url = "https://api.remove.bg/v1.0/removebg"

        with open(input_image_path, 'rb') as image_file:
            files = { "image_file": image_file }

            payload = {
                "size": "auto"
            }
            headers = {
                "Accept": "image/png, application/json",
                "x-api-key": API_KEY
            }

            response = requests.post(url, data=payload, files=files, headers=headers)
            response.raise_for_status()

            with open(output_image_path, 'wb') as f:
                f.write(response.content)
                print(f"Image downloaded and saved to {output_image_path}")

    except requests.RequestException as e:
        print(f"Error: {str(e)} ({input_image_path})")
        return str(e)
    
def iterate_over_directory(directory_path, result_directory):
    for root, _, files in os.walk(directory_path):
        for file in files:
            if file.lower().endswith(('.png', '.jpg', '.jpeg', '.webp', '.heic')):
                file_path = os.path.join(root, file)

                result_file_name = os.path.splitext(os.path.basename(file_path))[0] + '.png'
                result_file_directory = os.path.join(result_directory, os.path.basename(root))

                if not os.path.exists(result_file_directory):
                    os.makedirs(result_file_directory)

                result_path = os.path.join(result_file_directory, result_file_name)

                if not os.path.exists(result_path): # don't re-process images 
                    process_image(file_path, result_path)    

if __name__ == "__main__":
    INPUT_DIRECTORY = "./original-images/"
    OUTPUT_DIRECTORY = "./result-remove-bg/"

    if not os.path.exists(OUTPUT_DIRECTORY):
        os.makedirs(OUTPUT_DIRECTORY)

    iterate_over_directory(directory_path=INPUT_DIRECTORY, result_directory=OUTPUT_DIRECTORY)

Before running this code, please download the original images that you want to re-process, and place them in a directory called original-images.

import os
import requests

API_KEY = "YOUR_CLIPDROP_API_KEY"

def process_image(input_image_path, output_image_path):
    try:
        url = "https://clipdrop-api.co/remove-background/v1"

        with open(input_image_path, 'rb') as image_file:
            files = { "image_file": image_file }

            payload = {
                "transparency_handling": "discard_alpha_layer"
            }
            headers = {
                "Accept": "image/png",
                "x-api-key": API_KEY
            }

            response = requests.post(url, data=payload, files=files, headers=headers)
            response.raise_for_status()

            with open(output_image_path, 'wb') as f:
                f.write(response.content)
                print(f"Image downloaded and saved to {output_image_path}")

    except requests.RequestException as e:
        print(f"Error: {str(e)} ({input_image_path})")
        return str(e)
    
def iterate_over_directory(directory_path, result_directory):
    for root, _, files in os.walk(directory_path):
        for file in files:
            if file.lower().endswith(('.png', '.jpg', '.jpeg', '.webp', '.heic')):
                file_path = os.path.join(root, file)

                result_file_name = os.path.splitext(os.path.basename(file_path))[0] + '.png'
                result_file_directory = os.path.join(result_directory, os.path.basename(root))

                if not os.path.exists(result_file_directory):
                    os.makedirs(result_file_directory)

                result_path = os.path.join(result_file_directory, result_file_name)

                if not os.path.exists(result_path): # don't re-process images 
                    process_image(file_path, result_path)    

if __name__ == "__main__":
    INPUT_DIRECTORY = "./original-images/"
    OUTPUT_DIRECTORY = "./result-clipdrop/"

    if not os.path.exists(OUTPUT_DIRECTORY):
        os.makedirs(OUTPUT_DIRECTORY)

    iterate_over_directory(directory_path=INPUT_DIRECTORY, result_directory=OUTPUT_DIRECTORY)

Before running this code please:

download the original images that you want to re-process, and place them in a directory called original-images
run the command: pip install pillow rembg

from PIL import Image
from rembg import new_session, remove
import os

MODEL_NAME = "sam"
SESSION = new_session(MODEL_NAME)

def process_image(input_image_path, output_image_path):
    input = Image.open(input_image_path)
    output = remove(input)
    output.save(output_image_path)
    print(f"Image saved to {output_image_path}")
    
def iterate_over_directory(directory_path, result_directory):
    for root, _, files in os.walk(directory_path):
        for file in files:
            if file.lower().endswith(('.png', '.jpg', '.jpeg', '.webp', '.heic')):
                file_path = os.path.join(root, file)

                result_file_name = os.path.splitext(os.path.basename(file_path))[0] + '-sam.png'
                result_file_directory = os.path.join(result_directory, os.path.basename(root))

                if not os.path.exists(result_file_directory):
                    os.makedirs(result_file_directory)

                result_path = os.path.join(result_file_directory, result_file_name)

                if not os.path.exists(result_path): # don't re-process images 
                    process_image(file_path, result_path)

if __name__ == "__main__":
    INPUT_DIRECTORY = "./original-images/"
    OUTPUT_DIRECTORY = "./result-sam/"

    if not os.path.exists(OUTPUT_DIRECTORY):
        os.makedirs(OUTPUT_DIRECTORY)

    iterate_over_directory(directory_path=INPUT_DIRECTORY, result_directory=OUTPUT_DIRECTORY)

Before running this code, please download the original images that you want to re-process, and place them in a directory called original-images.

import os
import requests

API_ENDPOINT = "YOUR_AZURE_ENDPOINT"
API_KEY = "YOUR_AZURE_API_KEY"

def process_image(input_image_path, output_image_path):
    try:
        url = API_ENDPOINT + "computervision/imageanalysis:segment?api-version=2023-02-01-preview&mode=backgroundRemoval"

        with open(input_image_path, 'rb') as image_file:
            headers = {
                "Content-Type": "application/octet-stream",
                "Ocp-Apim-Subscription-Key": API_KEY
            }

            response = requests.post(url, data=image_file, headers=headers)
            response.raise_for_status()

            with open(output_image_path, 'wb') as f:
                f.write(response.content)
                print(f"Image downloaded and saved to {output_image_path}")

    except requests.RequestException as e:
        print(f"Error: {str(e)} ({input_image_path})")
        return str(e)
    
def iterate_over_directory(directory_path, result_directory):
    for root, _, files in os.walk(directory_path):
        for file in files:
            if file.lower().endswith(('.png', '.jpg', '.jpeg', '.webp', '.heic')):
                file_path = os.path.join(root, file)

                result_file_name = os.path.splitext(os.path.basename(file_path))[0] + '-azure.png'
                result_file_directory = os.path.join(result_directory, os.path.basename(root))

                if not os.path.exists(result_file_directory):
                    os.makedirs(result_file_directory)

                result_path = os.path.join(result_file_directory, result_file_name)

                if not os.path.exists(result_path): # don't re-process images 
                    process_image(file_path, result_path)    

if __name__ == "__main__":
    INPUT_DIRECTORY = "./original-images/"
    OUTPUT_DIRECTORY = "./result-azure/"

    if not os.path.exists(OUTPUT_DIRECTORY):
        os.makedirs(OUTPUT_DIRECTORY)

    iterate_over_directory(directory_path=INPUT_DIRECTORY, result_directory=OUTPUT_DIRECTORY)

PreviousAI Backgrounds Competitors Benchmark (Claid.ai, Phot.ai, Bria.ai)NextChangelog

Last updated 1 month ago