File download fails because a single file of Google drive data is too large, example UniSIN: , 457G(https://drive.google.com/file/d/15Pz2pr9u1nS809wXYGroEDFEprBVCTF0/view?usp=sharing)

It is appreciated to publish new datasets for indoor environment, and thanks for your working. I have some questions of the Simsin dataset.

1. Where can I find the camera intrinsics of Simsin dataset? The dataset zip does include the readme or camera intrinsics for the dataset.
2. Whether a dataset.py file that reads the simsin dataset can be published ?

Thanks for your working and looking forward to your reply

Hi, thanks for the wonderful work! I have made a evaluation on NYU-V2 test dataset and the code is based on demo.py and the pretrain model provided . I add the h5py read function and evaluation result calculation funcion.

However, I got a result lower than the paper mentioned. So I wonder whether the evaluation code is wrong or the model is wrong? The result and evaluation code is following.

Thanks for your working and looking forward to your reply

evaluation result: val_error/abs_rel | val_error/sq_rel | val_error/rmse | val_error/rmse_log | val_error/lg10 | val_acc/a1 | val_acc/a2 | val_acc/a3 0.17270 0.14038 0.59941 0.21287 0.07320 0.73734 0.93800 0.98530

evaluation code(the py file isn't supported, turn it to txt): nyutest_demo.py.txt

When you use zed2i camera to collect data, Just hold it in your hands or use others stabilizing device? I found out when I tried, the video will shake when you hold it directly, Is there any way you can stabilize the zed2i camera while you're collecting data, thank you very much

Hi, Thank you so much for releasing your code. I am trying to run the evaluation script for NYUv2 dataset. Based on the README the format of the data should be like this:

├── NYUv2
       ├── img_val
          ├── 00001.png
          ......
       ├── depth_val
          ├── 00001.npy
          ......
          ......
       ├── NYUv2.txt

I have downloaded NYUv2 labeled dataset from here which is a .m file. Is this the dataset you used for evaluation? if yes do you have any scripts on how to extract data from this .m file compatible with the format mentioned in the README?

What is the 1.312 constant in output_to_depth function? And what are the 0.1 and 10 inputs to the function? is it based on the training data and should change during inference? In the demo visualization you use 0.1 and 5 instead of 0.1 and 10 Is the output of output_to_depth in meters? and output of the net (the sigmoid) is disparity? I didn't see any reference in the repo or the paper... Thanks!

Hi, thanks for releasing the code!

I have several questions after reading the execute_func.py:

• At L78, the DPT is initialized with invert=True, which means the output is already depth. While at L253, a division is performed again to convert the output of DPT to depth. Is there a comment error here, since from what I understand, the code at L254 seems to be correct.
• At L378, the pseudo_depth error is computed between outputs["fromMono_dep"] and outputs[('depth', 0, 0)], which have different scales. Should outputs["fromMono_dep"] be replaced by target_depth at L353, since its scale has been aligned.

Looking forward to your reply.

Best regards!

Hi,

Thanks for your nice work. I want to generate data from HM3D. Could you share the script for how to generate stereo data with depth with me.

Thank you!

I was wondering what is the motivation for using this scaling factor during evaluation? depth_pred *= torch.median(depth_gt) / [torch.median(depth_pred)](url) https://github.com/facebookresearch/DistDepth/blob/dde30a4cecd5457f3c4fa7ab7bf7d5c8ea95934a/execute_func.py

If we remove this scaling, the results are not aligned with what is reported in the paper. For NYUv2 dataset, the RMSE increases from 0.58 to 0.99

Can you please explain why did you use that scaling during evaluation? Is it reasonable to scale-up from ground truth information?

Also in compute_depth_errors(), how did you decide on 1.25 as a threshold?

i test bash eval.sh

but have a issues :FileNotFoundError: [Errno 2] No such file or directory: 'ckpts-distdepth-M-101-SimSIN-DPTLegacy/pose_encoder.pth'

where can download pose_encoder.pth.

i unzip ckpts-distdepth-M-101-SimSIN-DPTLegac only have depth.pth and encoder.pth