SHI-Labs / Matting-Anything

Matting Anything Model (MAM), an efficient and versatile framework for estimating the alpha matte of any instance in an image with flexible and interactive visual or linguistic user prompt guidance.

https://arxiv.org/abs/2306.05399

SHI-Labs/Matting-Anything Issues

HuggingFace demo down
Updated 3 months ago
webui报错
Closed a year ago6
An error occurred while running python gradio_app.py.
Closed a year ago6
pip install --upgrade diffusers[torch]
Closed a year ago3
Inference on own image trimap pair
Updated 8 months ago1
Inference on custom dataset
Updated 9 months ago
Request for adding object function
Updated 10 months ago1
evaluation result is inconsistent with Table1 of the paper on the ppm100
Closed a year ago1
Connection error when running gradio_app.py
Closed a year ago1
Request for the Distinctions646 dataset
Closed a year ago2
Failed to build pycocotools - Python.h: No such file or directory
Closed a year ago3
Suggestion - Integrate MobileSAM into the pipeline for lightweight and faster inference
Closed a year ago1
May I ask when the complete dataset will be released?
Closed a year ago1
HuggingFace demo seems down
Closed a year ago1
training code release
Closed a year ago2
Question regarding smoothing of edges
Updated a year ago3
How long it takes to train MAM?
Closed a year ago2
Please list CUDA version as 11.7 in docs
Closed a year ago1
Looking forward to GETTING_STARTED.md section update soon
Closed a year ago1
For Video?
Closed a year ago3
Thanks for wonderful word .Question about text prompt
Closed a year ago5