wanghy

I got the same results, guess you could check the issue mentioned in https://github.com/kwea123/ngp_pl/issues/95 as the author uses the code of ngp_pl, and https://github.com/jetd1/NeRFusion/issues/8#issue-1409552026 also shows similar results with 0...

Hi @saulgooodman, this error message does not provide any information about why this compilation error happens, can you try to check the compiler output for a more detailed error message...

Hi @saulgooodman, it looks like this error is likely to be related to your system and compiler. As I am not familar with compilation using Windows, I would suggest double-checking...

Hi @mattiapiz, this is a cool idea, and Co-SLAM should be able to achieve this. I think that you might have done something wrong. The screenshot you provide is not...

Hi @mattiapiz, thanks for providing those details. As far as I can see, the surface reconstruction is not perfect, but still okay. These blocky color artifacts seem more related to...

Hi @mattiapiz, you may need to increase n_bins rather than decreasing it. If the problem still exists, maybe you could send me an email with your data, and I can...

Hi @mattiapiz, thank you for the data. Now I figure out what is the problem. Basically, the data type of your bounding box is int instead of float. You need...

Hi @ming82871, thanks for your interest in our work. There are several potential reasons for this issue. 1) For rendering these results, have you used depth-guided sampling? As our truncation...

Hi @DelinQu, the coordinate system will not affect the reconstruction or pose evaluation. We use the OpenGL coordinate system in the code. Since ScanNet uses the OpenCV coordinate system, we...

Hi @Lilyo , Thanks for your interest in our work. I am currently in the process of cleaning up the code base and I will try to release the code...