Closed lasxz closed 5 years ago
The .npy contains an array with the depth value for each pixel. You can load the file using the np.load function of numpy. The depth values are in meters.
Thank you very much.
How can point clouds (x, y, z) be recovered from depth values?
Assuming that your image is a 360° equirectangular panorama, the (u,v) coordinates in your image are just the latitude and longitude of each point. Have a look at our paper for the details of the math on equirectangular projections.
The output of your program has only one image and one .npy file. How to get the predicted depth value of the image?