hkchengrex / XMem

[ECCV 2022] XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
https://hkchengrex.com/XMem/
MIT License
1.72k stars 191 forks source link

How is the mask of the first frame made? #116

Closed wang-shuaikang closed 1 year ago

hkchengrex commented 1 year ago

Can you be more specific?

wang-shuaikang commented 1 year ago

Can you be more specific? Hello, there are rgb files and annotation files in the input data format required by the XMem project, but the annotation file can be the first frame, so how can I get the annotation of the first frame when inputting the rgb file, and add the first frame Add the annotation of one frame to the annotation file, then use the rgb file and the annotation file of only the first frame to generate the annotation file of the next frame, and obtain the binary mask file of each frame

hkchengrex commented 1 year ago

That depends on your application. You can use our GUI tool for manual annotation.

wang-shuaikang commented 1 year ago

That depends on your application. You can use our GUI tool for manual annotation.

ok