About the metrics of preprocessed Co3d_v2 and the post-training step
VillardX opened this issue · comments
Hi, thanks for your great work. It really works well on my own dataset with your pretrained model.
Here I still have some questions.
- The readme provides the preprocess.py of dataset co3d_V2, I wonder the some infos about the preprocessed data.
- I wonder what is the metrics of depth map? I see when training, you divided it by 65535 in co3d.py. Does it mean meters after division?
- And the
$T$ vector in your preprocessed output is in meters? - Are the camera extrinsics
$R$ C2W? - Is 'selected_seqs_test.json' the list of rgb index to make pairs?
- The provided pretrained model works well on my own dataset. However, the global alignment step is time consuming.
- I find that the train loss is essentially consisted of a image-pair, not including multi-view contents, which means the global alignment is a post-processing step and is not included in the training step. Is my understanding correct?
- In my situation, the trainset input views' poses are the same as the testset. Is it feasible to use my own trainset to post-train your provided model and avoid global alignment in the inference step. Could you please give me some advice?
Best regards,
VillardX