Meta:segment anything

介绍地址：https://ai.facebook.com/research/publications/segment-anything/

GitHub地址：https://github.com/facebookresearch/segment-anything

Abstract

We introduce the Segment Anything (SA) project: a new task, model, and dataset for image segmentation. Using our efficient model in a data collection loop, we built the largest segmentation dataset to date (by far), with over 1 billion masks on 11M licensed and privacy respecting images. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks. We evaluate its capabilities on numerous tasks and find that its zero-shot performance is impressive -- often competitive with or even superior to prior fully supervised results. We are releasing the Segment Anything Model (SAM) and corresponding dataset (SA-1B) of 1B masks and 11M images at \href{https://segment-anything.com}{https://segment-anything.com} to foster research into foundation models for computer vision.

SEEM: Segment Everything Everywhere All At Once

地址：https://huggingface.co/spaces/xdecoder/SEEM

Instructions:

🎈 Try our default examples first (Sketch is not automatically drawed on input and example image);

🎈 For video demo, it takes about 30-60s to process, please refresh if you meet an error on uploading;

🎈 Upload an image/video (If you want to use referred region of another image please check "Example" and upload another image in referring image panel);

🎈 Select at least one type of prompt of your choice (If you want to use referred region of another image please check "Example");

🎈 Remember to provide the actual prompt for each promt type you select, otherwise you will meet an error (e.g., rember to draw on the referring image);

🎈 Our model by defualt support the vocabulary of COCO 133 categories, others will be classified to 'others' or misclassifed.