search

megvii-research / RealFlow

The official implementation of the ECCV 2022 Oral paper: RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videos
Other
94 stars 11 forks source link

About M-step #19

Open Eryo-iPython opened 1 year ago

Eryo-iPython commented 1 year ago

thanks for your good work, I have some questions for M-step

  1. Using C+T to generate new dataset G1.
  2. Using G1 to train RAFT get new weight C+T+G1.
  3. Using C+T+G1 to generate dataset G2. my question is that which weight should used to train RAFT in the next step? In the other words, I should use the weight C+T+G1 to train RAFT or keep C+T to train it on dataset G2？