search

jzhangbs / Vis-MVSNet

Visibility-aware Multi-view Stereo Network
MIT License
235 stars 27 forks source link

What's the use of GNRefine? #1

Open NewMesc opened 3 years ago

NewMesc commented 3 years ago

Hi, thanks for your nice code and work! After reading the release version of code and your paper, I found GNRefine module not described in paper but was a part of VisMVSNet (although related code was comment out). So, what's the use and the role of GNRefine, looking forward to your answer!

jzhangbs commented 3 years ago

It's a depth map refinement. It's described in Sec 3.3 of Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinement. We find the improvement is marginal so we disable it.

NewMesc commented 3 years ago

Got it. I am trying to reproduce the result on Tanks and Temples which presented in your paper, but only reahced 57.09 on intermediate leaderboard. And I found your newest submission whcih contained pretrained model and fusion codes. Which dataset was this checkpoint trained on? Could this checkpoint reproduce the T&T result presented in paper?

jzhangbs commented 3 years ago

The model is trained on BlendedMVS. This checkpoint is used by the benchmark result. But the fusion script cannot be released. The provided script is re-implemented by me afterward and I didn't test it on this benchmark. So I cannot guarantee that you can reproduce the same result, but it should still be in the top tier.