qsisi

Thank you so much for your explanations. Also I got several new questions about the Sinkhorn. I'm asking here if you don't mind. :) In my understanding, the sinkhorn operation...

Yes, I totally know that a doubly stochastic matrix means a matrix that each row and column of it sums to one, but the confusing point for me is that...

Sorry to bother you again, I notice that in superglue, the sinkhorn operation is implemented like this: https://github.com/magicleap/SuperGluePretrainedNetwork/blob/ddcf11f42e7e0732a0c4607648f9448ea8d73590/models/superglue.py#L152 Compared to the implementation in RPMNet, there are a lot of differences,...

Thanks for your answer, although I still could not understand the difference between [your implementation](https://github.com/yewzijian/RPMNet/blob/2cbdfe91d66d2076b0a94d2ee7ff362ba6e272f9/src/models/rpmnet.py#L46) compared with the one in [SuperGlue](https://github.com/magicleap/SuperGluePretrainedNetwork/blob/ddcf11f42e7e0732a0c4607648f9448ea8d73590/models/superglue.py#L143). Here I got a new question :) In your...

Thanks for your timely reply! During these days I retrained the DCP_v2 for 250 epochs using the following settings: unseen -> True: first 20 classes for training, and the rest...

> Hi, > > For some reason, ceres does not find glog. However the superbuild should have installed it along all other external dependencies. Can you check in the directory...

Thanks for your clarification! Also, I have a question on the positional encoding implemented here: ``` for j in range(h): for k in range(w): w1, w2, w3 = torch.split(Kinv @...

Also, the position encoding normalizes the images to [-1, -1] by dividing the intrinsic with hpix&wpix, which is cy * 2 and cx * 2 in the code, why not...

Sorry to bother you again, but did someone find that the gt extrinsic of Matterport is not accurate?

The extrinsics is accurate, looks like I missed the flip_axis: https://github.com/crockwell/far/blob/main/mp3d_loftr/src/utils/dataset.py#L222 which was found in your FAR implementation. However, it seems like you didn't add the flip_axis in this 8-ViT...