where can I find kitti disparity map

[wlgcqh]

No description provided.

[mrharicot]

Hi,

Which disparities are you looking for?

-Clement

[wlgcqh]

disp = cv2.imread(path + "/training/disp_noc_0/" + str(i).zfill(6) + "_10.png", -1) in utils/evaluation_utils.py 38 lines,I'm looking for kitti disparity map ground truth.

[mrharicot]

They are the KITTI 2015 stereo disparities, you can find them here:
http://www.cvlibs.net/download.php?file=data_scene_flow.zip

-Clement

[wlgcqh]

thanks a lot for your response! it's a fantastic work in this year

[salmankh47]

@mrharicot How can I convert sparse disparity map to dense?
The disparity provided in scene_flow dataset looks sparse.

[1475015695]

@mrharicot How can I convert sparse disparity map to dense?
The disparity provided in scene_flow dataset looks sparse.

Did you soved it?I met the same issue

[royshil]

you could use maxpooling to dense up the sparse map in expense of resolution

kittiD = cv2.imread('training/disp_noc_0/000000_10.png',0)
import skimage.measure
plt.imshow(skimage.measure.block_reduce(kittiD, (5,5), np.max))