fidler-lab / polyrnn-pp-pytorch

PyTorch training/tool code for Polygon-RNN++ (CVPR 2018)
703 stars 106 forks source link

Request new feature one click annotation #22

Open Po-Hsuan-Huang opened 5 years ago

Po-Hsuan-Huang commented 5 years ago

Thanks for open source this project.

I am looking for a tool to automatically semantically segment videos instead of frame by frame. This tool is good in that it has transferable learning to automatically segment one instance, but it still takes time to label (1) all instances in one frame one by one. (2) same instance through multiple frames. It will be really cool if I can segment all instances of the same category in one frame by one click, and automatically segment the same instances in the following frames.

abinjoabraham commented 5 years ago

@Po-Hsuan-Huang That would be a great idea. Looking forward to see something like that. Are you gonna work on this project Mr. Huang ? I would be glad to join you if you wanna work on something like that.

Jacoobr commented 5 years ago

@Po-Hsuan-Huang , Your idea is every useful and great for 'video instance segmentation task' if it can be implemented as a tool.