search

suhwan-cho / TMO

[WACV 2023] Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation
MIT License
56 stars 3 forks source link

. #6

Closed JawadTawhidi closed 1 year ago

JawadTawhidi commented 1 year ago

.

suhwan-cho commented 1 year ago

Hi, sorry for the late reply.

  1. I don't think that's a problem.
  2. You can refer to the official evaluation code (https://github.com/davisvideochallenge/davis).
  3. J and F score calculation can be found at official DAVIS evaluation code.
suhwan-cho commented 1 year ago

Unfortunately, I have deleted that code.

RAFT takes two images as its input. As I remember, the first input is the target frame and the second input is the source frame. When dealing with the last frame, you only need to use the target frame as the second input and the source frame as the first input.