Willyzw

Same issue for me. After some googling, it seems to have something to do with the special combination of TensorFlow 1.12 + RTX 2080. So after upgrading TensorFlow from 1.12.0...

Hi, I encounter the same question why the third one of the homogenous coordinates instead of last. Any idea about it?? Btw the replacement for the clamped values are different...

I can confirm the flaw. But the weird thing is that the disparity map generated with the fix is worse (less smoothed and many holes) than the original one.

> @whubaichuan sorry, I don't have wechat. > I think all you need is paste a few lines in mvsnet.py . > If there still having OOM problem please delete...

Hi, I can confirm the observed degraded results. Sofar I have trained the Neuralangelo model on Barn and Courthouse scenes. Training logs on Wandb can be accessed here: https://api.wandb.ai/links/willyzw/whf9tz8o I...

Indeed, sorry I didn't notice it. The GT meshes of 7-scenes data are included in the provided link. However I couldn't find the GT meshes of scannet data. Although the...

No problem, the metric one from the GT poses is preferred. Thanks a lot! By inconsistency in the coordinate system, I actually mean the GT poses of the scene 0580...

Thanks for your quick check. Lately I also received the reply (link: https://github.com/zju3dv/manhattan_sdf/issues/57) from the Manhattan SDF author, which clarified that the coordinate inconsistency was caused by a rotation they...

Hi @phamquandung, first you need to get it installed, I mostly get help from this PR https://github.com/ToniRV/NeRF-SLAM/pull/12. To run the evaluation, you will also need to add the flag `--eval`...

Hi @ToniRV glad to receive your reply! You can please check my changes here https://github.com/ToniRV/NeRF-SLAM/compare/master...Willyzw:NeRF-SLAM:master The results were run after the first commit, so I hardly change any functional stuff...