Very interesting paper, I did not know you could get such results using traditional image processing.
From the paper:
Since only average feature vector values of $R_1$ and $R_2$ need to be
found, we use the integral image approach as used in  for
computational efficiency. A change in scale is affected by scaling the
region $R_2$ instead of ...
The original transformer is a feedforward neural network (FFNN)-based architecture that makes use of an attention mechanism. So, this is the difference: an attention mechanism (in particular, a self-attention operation) is used by the transformer, which is not just this attention mechanism, but it's an encoder-decoder architecture, which makes use of other ...
Probably closely related to the problem of interest would be
something akin Neural Radiance Fields (NeRF for short) https://www.matthewtancik.com/nerf.
The model takes several images from different angles and view of the scene and learns a 3d representation of the scene, that can be used to sample novel views of this scene (not present in the training data).
Depth maps are created using principles of photometry (method of measuring light).
The depth maps (rather images) you took from the website are "images" not exact depth "maps". So by default when you pull out a png image from a webpage, it will be saved in "RGB". That is the reason you got an array with 3 layers. In practice, it ...
Neural networks are not invariant to translations, but equivariant,
Invariance vs Equivariance
Suppose we have input $x$ and the output $y=f(x)$ of some map between spaces $X$ and $Y$. We apply transformation $T$ in the input domain. For general map,output will change in some complicated and unpredictable way. However, for certain class of maps, change of ...