hkchengrex / MiVOS

[CVPR 2021] Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion. Semi-supervised VOS as well!

Home Page:https://hkchengrex.com/MiVOS/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Is that possible this work in real-time case

mathmax12 opened this issue · comments

Hi
Thanks for sharing the amazing work.
Does the work support real-time case?
If not what change do you recommend for that?
Thanks.

Can you elaborate on what properties do your real-time case needs? (speed/online/long sequences?)

For example, processing the video stream from a camera in real-time 30FPS.

Speed-wise, the current model can handle it with PyTorch's AMP enabled in the single object setting. But then there are also considerations regarding inputs (this is after all an interactive method) and memory (feature bank growing over time as in STM).