Yiming Xie

I got single-layer mesh using http://www.open3d.org/docs/release/tutorial/pipelines/rgbd_integration.html, And I got following result (sample frames with the interval of 10): dist1 0.100 dist2 0.083 prec 0.612 recal 0.577 fscore 0.590 l1 0.179

Hi, you can use vertical images but do not rotate them by 90 degrees as shown in your post figure.

Hi, 可能是2d feature extraction的时候训练数据都是横着的图像，所以竖着的图像效果不太好。但是neuralrecon应该也会受这个影响而效果差一些，所以我也不太确定。不过还是可以尝试这么处理: 如果是自动转了90度，你可以试试在进2d backbone之前把图像转-90度，出来的feature map再转90度回来: https://github.com/neu-vi/PlanarRecon/blob/main/models/planarrecon.py#L83. 这样你back projection的内参/外参也不用变了。

@wangshuailpp @nbansal90 Hi, you can check the camera coordinate and the world coordinate from ARCore, which need to be consistent with the corresponding coordinates in ScanNet: The camera coordinate in...

Same problem here. Updating Xcode-select or changing numpy version didn't work.

> what's your full logs? the numpy need to be installed in env Blender.app//Contents/Resources/3.3/python/bin/python3.10, you can list the packages: Sure: pip list: ``` (infinigen) ➜ infinigen git:(main) ✗ Blender.app//Contents/Resources/3.3/python/bin/python3.10 -m...

> here is no error, just some warnings, you seem have successed. try to run the hello world example Oops, Sorry I didn't notice that. It works now. Thank you...

Hi, I will add the code to generate the error map this week :) Thanks Yiming

Hi, Please check my latest commit for saving the error maps. You need to set error_map=False (https://github.com/neu-vi/PlanarRecon/blob/main/tools/eval3d_geo_ins.py#L67) if you want to save the error maps. Best

Thank you for your interest in our work! I will take a look soon ...