Could you upload the dataset to Google Drive, please? There is some trouble when downloading the dataset vis Dropbox. Thank you very much!

Thank you for your work！
According to your code:
ext_NIR2THR = np.concatenate([calib['R_nir2thr'], calib['T_nir2thr']*0.001], axis=1) # mm -> m scale conversion.
ext_NIR2RGB = np.concatenate([calib['R_nir2rgb'], calib['T_nir2rgb']*0.001], axis=1)
ext_THR2NIR = np.linalg.inv(np.concatenate([ext_NIR2THR, [[0,0,0,1]]],axis=0))
ext_THR2RGB = np.matmul(np.concatenate([ext_NIR2RGB, [[0,0,0, 1]]],axis=0), ext_THR2NIR)
ext_RGB2NIR = np.linalg.inv(np.concatenate([ext_NIR2RGB, [[0,0,0,1]]],axis=0))
ext_RGB2THR = np.linalg.inv(ext_THR2RGB)

I get the ext_RGB2THR, can it express extrinsic parameters from left rgb to left thr?

Hi, @UkcheolShin

Thank you for your work, your work provides valuable data for multimodal visual tasks.

After downloading and decompressing the compressed file, I found that most of the files were damaged. For example, an error occurred when I decompressed to nir/right/8756.png in _2021-08-06-10-59-33 (I re-downloaded the compressed file and the same error occurred at the same location).

Could you please check the status of each compressed package?

The list of files that failed to decompress is as follows:

image:
_2021-08-06-10-59-33.tar.bz2
_2021-08-06-11-23-45.tar.bz2
_2021-08-06-11-37-46.tar.bz2
_2021-08-06-16-19-00.tar.bz2
_2021-08-06-16-45-28.tar.bz2
_2021-08-06-16-59-13.tar.bz2
_2021-08-06-17-21-04.tar.bz2
_2021-08-06-17-44-55.tar.bz2
_2021-08-13-15-46-56.tar.bz2
_2021-08-13-16-14-48.tar.bz2
_2021-08-13-16-50-57.tar.bz2
_2021-08-13-17-06-04.tar.bz2
_2021-08-13-21-18-04.tar.bz2
_2021-08-13-21-36-10.tar.bz2
_2021-08-13-22-03-03.tar.bz2

proj_depth:
_2021-08-06-10-59-33.tar.bz2
_2021-08-06-11-23-45.tar.bz2
_2021-08-06-16-45-28.tar.bz2
_2021-08-06-17-44-55.tar.bz2
_2021-08-13-15-46-56.tar.bz2
_2021-08-13-16-08-46.tar.bz2
_2021-08-13-16-31-10.tar.bz2
_2021-08-13-17-06-04.tar.bz2
_2021-08-13-21-18-04.tar.bz2
_2021-08-13-21-36-10.tar.bz2
_2021-08-13-22-03-03.tar.bz2
_2021-08-13-22-16-02.tar.bz2

Hello!
In the paper, it is mentioned that the dataset consists of 24 scenes, but there are only 20 scenes available in the download path. I would like to inquire if some parts of the dataset are not downloadable.

Thank you for releasing the dataset.

Can you tell me how to obtain the projection depth map? I use y=K_ nirL * extrinsic_lidarL2nir * x cannot obtain the same depth map as you

Is it possible to use the dataset for training which in your previously published method "Self-supervised Depth and Pose from Monocular Thermal Video " models

Hi I recently downloaded the dataset the thermal image looks all black when you view it in photo viewer can someone tell me how to fix this so i can actually view in a viewer

I computed HFOVs from the rectified camera matrices provided in calib.npy with the following equation:
$HFOV = 2 * \text{atand}(n_x / (2 f_x))$
where:

• atand: inverse tangent in degrees
• n_x: image width
• f_x: horizontal focal length (in units of pixels)

this yields:

• thermal left: 79 degrees (vs 45 in the paper)
• rgb left: 77 degrees (vs 82.2 in the paper)
• nir left: 90 degrees (vs 69 in the paper)

I checked the one camera for which I could confidently find the HFOV, the left NIR camera from the Intel RealSense D435i, and the spec sheet lists the HFOV as 91.2 degrees (see table 3-13). It appears the 69 degree HFOV listed in the paper was taken from either the color sensor (table 3-16) or the standard imager (table 3-12), while the D435i uses the wide imager (as listed in table 3-11).

My guess is that HFOV listed for the RGB camera in the paper is correct and that the rectified RGB images lose a slight bit of that FOV. But it seems the thermal and NIR FOVs listed in the paper are incorrect. Can you confirm whether this is the case?

Thank you for releasing the dataset.

Also, can you please release the code for depth estimation...

Thank you

Hello @UkcheolShin,

Thank you for releasing the dataset.

Also, can you please release the code for depth estimation...

Thank you
Gopi