ewrfcas

https://github.com/apchenstu/mvsnerf/blob/6e0111188ff92b13229482a95a2fb4eaddbc2971/train_mvs_nerf_pl.py#L182 There are BNs in MVSNet, which are implemented differently from training.

Are DTU results reported in the paper trained on 640 or 1280?

1

Thanks for your good work! I have not seen any discussion of the input resolution in the paper.

It seems that shapnet is trained with multi-view supervision and test with single-view. Can I test shapenet data with multi-view?

The compiled isosurface fails to work in ppc64le.

Thanks for your great jobs! Can you release the code or methods to get the heat pictures? And what is the useage of fake-mask.jpg in /heat?

https://github.com/zihangdai/xlnet/blob/5cd50bc451436e188a8e7fea15358d5a8c916b72/modeling.py#L529

As discussed in this issue (https://github.com/mihaidusmanu/d2-net/issues/26#issuecomment-543748938), there are negligible differences between Megadepth images and D2-Net images. If we use the intrinsic and extrinsic provided in 'train-data/megadepth-indices', can we directly use...

Question about the image undistortion

8

Thanks for your great work! I am using your undistort_reconstructions.py to undistort megadepth images, but some problems have happened. There are 195 scenes in megadepth at all, but only 163...

Config questions of notebook and scripts of feature matching

2

Thanks for your excellent work. In 'FeatureMatching/scripts/reproduce_test/outdoor_ds_quadtree.sh', 'configs/loftr/outdoor/loftr_ds_quadtree.py' is used. But this config is different from 'cvpr_ds_config.py'. In 'FeatureMatching/notebooks' only default settings from 'cvpr_ds_config.py' are used. Which setting should be...