Shuaifeng Zhi

Hi @MisEty, I have uploaded the config file for ScanNet in the repo now, which has the same hyper-parameters to replica. As to pre-trained models, I will have a look...

Hi @Unrealluver, Thanks for your insterests and sorry for my late reply as I way away office for last few months. Do you mean the multi-view Bayesian or Average fusion...

Hi @jmwang0117, As far as I can well, the most straightforward way could be setting the instances that you did not want to predict as label 0 (void class), so...

Hi, Sorry for the late reply. 1. As mentioned in the paper, I used Habita-Sim to render images, semantics using my pre-generated random poses. If you are interested in generating...

Hi all. Actually I put all the parsed scannet images per scenes into a unified folder called "renders", where the subfolders "pose", "color", "depth" contains the corresponding data. I have...

@suljaxm 的确，应该是g2o的版本问题。我本来也有同样的问题，之后我删除了github上的最新版本g2o,采用了高博提供的g2o，程序就能正常编译了。

Also look forward to the PASCAL set-up.

Hi @Maguire1999 , The NDC space used in NeRF is mainly designed for training MLP in LLFF-type unbounded scenes where all cemeras face towards certain directions (you can image that...

Hi @jmwang0117 , Actually we did not change the image rendering results as well as visualisation. The images shown in tensorboard and mp4 video are masked using the void regions:...

Hi @mtk380, Could you let me know what are the detailed problems you met during mesh extraction? So I could discuss with you and fix possible issues in my codebase...