With Synthetic Dataset Training Codes about dkm HOT 6 CLOSED

Hi again. I no longer recommend training with synthetic data. We mainly did this for comparison with PDCNet.
I will push an indoor version which is trained on megadepth + scannet, which we found to work the best.

from dkm.

Also, apologies for things not being consistent, the code is still in active development and the public version may change over time.

from dkm.

@TWJianNuo The training is now updated for DKMv2, including scannet training. For scannet you need to download the scannet dataset and indices (see https://github.com/zju3dv/LoFTR/blob/master/docs/TRAINING.md). Note that we only used every 10 frames, since the full scannet dataset is extremely large.

from dkm.

Ahh... I am confused. May I double-check the following facts:

For DKM:

• DKMv2 outdoor: Trained using MegaDepth Only.
• DKMv2 indoor: Trained using MegaDepth + Scannet.

While in the LoFTR paper, they:

• LoFTR outdoor: Trained using MegaDepth Only.
• LoFTR indoor: Trained using Scannet Only.

In the curret Arxiv paper:
Tab.1 is the results from DKM v1, trained on MegaDepth or MegaDepth + Synthetic?
Tab.4 is also the results from DKM v1 but only trained on MegaDepth Dataset

Thanks!

from dkm.

@TWJianNuo yes, the pre print contains our previous approach with synthetic data and is not up to date. We are continously improving the approach and will soon (in around a month) release an updated preprint. Im dorry if this complicates any reproducing from your part.

from dkm.

Not at all! I really appreciate your prompt reply and well-maintained codebase!

Thanks!

from dkm.