Remove image background using advanced AI models including U-Net, BiRefNet, and SAM with support for multiple input formats and GPU acceleration
84
{
"context": "This evaluation assesses how well the engineer uses the rembg package to process RGB24 binary video streams for background removal. The focus is on correctly reading binary pixel data, converting it to appropriate formats for rembg processing, and efficiently handling frame-by-frame operations.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Binary stream reading",
"description": "Correctly reads RGB24 binary data from input_stream using appropriate buffer size calculation (width * height * 3 bytes for RGB24 format)",
"max_score": 20
},
{
"name": "Image format conversion",
"description": "Converts raw RGB24 binary data into a format compatible with rembg (PIL Image, numpy array, or bytes) before processing",
"max_score": 25
},
{
"name": "rembg.remove() usage",
"description": "Uses rembg.remove() function to process each frame and remove the background",
"max_score": 25
},
{
"name": "Session optimization",
"description": "Uses rembg.new_session() to create a reusable session for processing multiple frames efficiently, avoiding repeated model loading",
"max_score": 15
},
{
"name": "Output image saving",
"description": "Saves processed frames as PNG images with correct zero-padded sequential naming (frame-0001.png, frame-0002.png, etc.)",
"max_score": 10
},
{
"name": "Frame counting",
"description": "Correctly tracks and returns the number of frames processed",
"max_score": 5
}
]
}Install with Tessl CLI
npx tessl i tessl/pypi-rembgevals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10