tessl install tessl/pypi-rembg@2.0.0Remove image background using advanced AI models including U-Net, BiRefNet, and SAM with support for multiple input formats and GPU acceleration
Agent Success
Agent success rate when using this tile
84%
Improvement
Agent success rate improvement when using this tile compared to baseline
0.94x
Baseline
Agent success rate without this tile
89%
{
"context": "This criteria evaluates how well the engineer uses the rembg package's post-processing capability for mask smoothing to improve the quality of background removal results. The focus is on correct usage of the post_process_mask parameter and proper application of the remove() function.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Import rembg",
"description": "Correctly imports the remove function from the rembg package (e.g., 'from rembg import remove')",
"max_score": 10
},
{
"name": "Basic remove usage",
"description": "Uses the rembg remove() function to process images for background removal in the remove_background() implementation",
"max_score": 20
},
{
"name": "File I/O handling",
"description": "Correctly reads input images from file paths and writes output images to file paths using appropriate methods (e.g., open with 'rb' mode for reading, write bytes or PIL Image save for output)",
"max_score": 15
},
{
"name": "post_process_mask parameter",
"description": "Correctly uses the post_process_mask parameter when calling remove(), setting it to True when smooth_mask argument is True",
"max_score": 30
},
{
"name": "Standard vs smoothed",
"description": "Implements compare_removal_quality() to call remove() twice on the same image: once without post_process_mask (or False) and once with post_process_mask=True",
"max_score": 25
}
]
}