Max Zhaoshuo Li 李赵硕

Settings for SGM

1

Hello: Thanks so much for open-sourcing the code. The presentation also looks nice! I wonder what settings did you use for your reported result for SGM, because there are lots...

How is point cloud generated?

1

Hi @nickponline Thank you so much for your work. I wonder how you generated the dense point cloud information. Is it via structure from motion? Thank you!

Church scene provided images and poses do not match

8

Dear authors, Thank you very much for the dataset! In the provided training scene "Church", the number of images does not match the number of poses (507 vs 644). Quite...

DINO encoder

1

Dear authors: Thank you for your great work! I wonder why you used DINOV1 instead DINOV2, which is more suitable for dense prediction task. Thank you!