Closed SwagJ closed 3 years ago
Hi, I haven't tested, but I think the inference pipeline should be able to work with any flow input.
Note the expansion layers only depend on optical flow and image features (from VCN image encoder). One could replace line 499-516 with PWC-Net and make sure the flow fields matches the resolution of original VCN outputs (where flow is computed on 1/4 image resolution).
Hi @gengshan-y ,
Thank you very much for your reply. Indeed, I have tried PWC-Net with your expansion pipline. However, I just have questions about your data augmentation.
Best,
From what I remember,
Hi @gengshan-y ,
Thank you for your reply. Indeed, 3D geometry is irrelevant to image augmentation. Just have one last question. Is that possible for your to provide the VCN model's AEPE on Synth Driving dataset with pretrained weight flow-things, if you happens to observe that?
Best,
Hi, I don't have that number. It would be straightforward to modify eval_flow.py to support evaluation on synthetic driving dataset, but I don't have cycles to work on it right now, thanks.
Hi @gengshan-y ,
Thank you for your reply. I will try that!
Best,
Hi @gengshan-y ,
Thank you for your great work. I just have a question. Have you tested the compatibility of your implementation with PWC-Net?