This is an LWIR stereo-hyperspectral database to develop HADAR algorithms for thermal navigation. Based on this database, one can develop algorithms for TeX decomposition to generate TeX vision. One can also develop algorithms about object detection, semantic or scene segmentation, optical or scene flow, stereo depth etc. based on TeX vision instead of traditional RGB or thermal vision.
Hello, I am very interested in your research and am reproducing your code, I found that the function unsupervised_S_pred_loss inside model.py in your TeX-Net, returns the variable 'S_pred' as the unnormalized value, and you save it for later use in the visualization.py. But the original variable 'img' (heatcube) which is subsequently used and saved is normalized, which results in the normalized value being subtracted from the unnormalized value in the subsequent visualization.py. How can this result in a correct resmap?
The unnormalized 'S_pred' is much smaller than the true value 'S_true', which means that the subtraction of the two is still 'S_true', and the 'S_res' obtained with the In the MATLAB code Check_TeX_Vision_for_TeXNet_Outputs to get TeX Vision, does it mean that 'S_true' is used directly to get TeX Vision instead of 'S_res'?
Hello, I am very interested in your research and am reproducing your code, I found that the function unsupervised_S_pred_loss inside model.py in your TeX-Net, returns the variable 'S_pred' as the unnormalized value, and you save it for later use in the visualization.py. But the original variable 'img' (heatcube) which is subsequently used and saved is normalized, which results in the normalized value being subtracted from the unnormalized value in the subsequent visualization.py. How can this result in a correct resmap?