Wuuu~

> I suspect that the author is just looking for innovations. This monocular depth estimation has no effect on training at all, and the final loss L1 weight is 0...

> Hi, D-Net is trained to estimate the depth map in absolute scale. If the scale of the test scene is significantly different from the scale of the training scenes,...

> Hi, I use DTU official pose as known prior to get colmap results by [triangulation with known camera poses](https://colmap.github.io/faq.html#reconstruct-sparse-dense-model-from-known-camera-poses)and then put it into gs for rendering. However, I found...

> Can you tell me your credentials and upload details, then I can have a look in the log files. In the meanwhile, what helped people with similar errors: >...

> Hello, when using python uploader to upload the point clouds, an error has occured. "ConnectionResetError: [Errno 104] Connection reset by peer" > > So I would like to ask...

Thank you for your attention. We conducted tests by converting the ground truth depth to normals using Eq. 10.

Thanks for your interest in our work！ We are working intensively to resolve this issue.

Hi, we referenced MonoSDF to generate high-resolution normals. You can find more information at: https://github.com/autonomousvision/monosdf/tree/main/preprocess.

> Dear Jiang: > > Thanks for your excellent work. > > I would like to know which light condition is used for monocular normal estimation on the DTU training...

> Hi, > > Thanks for the great work ! because 384 is the size for Omnidata-model, the dtu image size is 1200x1600, if I want to use monocular cues...