search

Epiphqny / VisTR

[CVPR2021 Oral] End-to-End Video Instance Segmentation with Transformers
https://arxiv.org/abs/2011.14503
Apache License 2.0
740 stars 96 forks source link

Inference with Tracking #4

Closed priya-dwivedi closed 3 years ago

priya-dwivedi commented 3 years ago

@Epiphqny - Excellent work. We would like to test this out for instance segmentation and tracking. Your inference.py file says that this code does video segmentation only, no tracking. The code also seems to be similar to the code used by DETR for segmentation. How do we do instance tracking along with segmentation? Could you please share thoughts or code for that.

Epiphqny commented 3 years ago

Hi@priya-dwivedi, thanks for your interest in our work. If the video is not larger than 36 frames, the tracking could be naturally realized with this code. If the frame number is larger than our default frame number, you could refer this https://github.com/Epiphqny/VisTR/issues/3