Running on Colmap Data

[g-gaurav]

Thanks for the great work. I was trying to run it on some images captured through my camera. I used the colmap to get the world matrices. But it is giving the following error while trying to run preprocess_camera.py

preprocess_cameras.py:87: DeprecationWarning: np.floatis a deprecated alias for the builtinfloat. To silence this warning, use floatby itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, usenp.float64here. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations mask_points_all.append(np.stack((xs,ys,np.ones_like(xs))).astype(np.float)) preprocess_cameras.py:45: DeprecationWarning:np.floatis a deprecated alias for the builtinfloat. To silence this warning, use floatby itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, usenp.float64 here. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations cur_l_1=Fj0 @ np.array([curx,cury,1.0]).astype(np.float) Number of points:0 preprocess_cameras.py:169: RuntimeWarning: Mean of empty slice. centroid = np.array(all_Xs).mean(axis=0) /home/kshitiz/miniconda3/envs/idr/lib/python3.7/site-packages/numpy/core/_methods.py:189: RuntimeWarning: invalid value encountered in double_scalars ret = ret.dtype.type(ret / rcount) /home/kshitiz/miniconda3/envs/idr/lib/python3.7/site-packages/numpy/core/_methods.py:263: RuntimeWarning: Degrees of freedom <= 0 for slice keepdims=keepdims, where=where) /home/kshitiz/miniconda3/envs/idr/lib/python3.7/site-packages/numpy/core/_methods.py:223: RuntimeWarning: invalid value encountered in true_divide subok=False) /home/kshitiz/miniconda3/envs/idr/lib/python3.7/site-packages/numpy/core/_methods.py:254: RuntimeWarning: invalid value encountered in double_scalars ret = ret.dtype.type(ret / rcount) Traceback (most recent call last): File "preprocess_cameras.py", line 244, in <module> get_normalization(opt.source_dir, opt.use_linear_init) File "preprocess_cameras.py", line 207, in get_normalization normalization,all_Xs=get_normalization_function(Ps, mask_points_all, number_of_normalization_points, number_of_cameras,masks_all) File "preprocess_cameras.py", line 175, in get_normalization_function centroid,scale,all_Xs = refine_visual_hull(masks_all, Ps, scale, centroid) File "preprocess_cameras.py", line 101, in refine_visual_hull points = points + center[:, np.newaxis] IndexError: invalid index to scalar variable.

[ahnaf1393]

@g-gaurav were you able to solve the problem? I am facing the same issue.

[eduardramon]

Hi @g-gaurav and @ahnaf1393 ! Have you checked if colmap was able to find the correct camera for each image in the scene?

[ahnaf1393]

I think they are correct @eduardramon. I will still recheck. By the way, does the origin of the world coordinate system matter in this case? I think for DTU the origin is associated with the robot hand carrying the camera. For me it is the first image that I take with my mobile camera.

[g-gaurav]

Hi @eduardramon and @ahnaf1393. Yes, it is working with colmap data. but there is a problem, we need to decide the scale_mat factor. because your object is not on the origin. and scale can be different. so I am not running this preprocessing script. Directly run the training code on the colmap camera matrix and images.

[ahnaf1393]

@g-gaurav Don't you need the scal_mat for running the training code? May I ask how you compute it?

[ghost]

@g-gaurav Have you solved the problem？

[siyangbing]

@g-gaurav Have you solved the problem？

+1