Almost always related to Texture Coordinate
The usual method is to plug a texture coordinate into a mapping node and then the mapping node into the vector input of the texture. The texture coordinate node controls how a texture’s position maps to a mesh’s surface. The mapping node let’s you make adjustments to that mapping. Example below:
I think I missed the part about the mice’s dreams, because I didn’t see anything about that in the article.
Regarding the method, they seem to have built a model to do the work. They show a training video and just record what happens to the mouse’s brain. They then make an algorithm that says, “ok, this part of the brain activates 98% of the time when the pixel at position #8 is black, and this part 96% of the time when pixel #30 is white, etc…”. They then use a different video, which wasn’t used for training, and feed it into the algorithm to predict how the mouses brain will react. Then compare prediction with reality, and see how reliable it is.
Not sure there is an associated paper, but this is what I got out of the article alone.
I finally got to learn blender during covid, think it was late version 2.X, early 3.X. I had gotten pretty decent, and even made a plugin, but haven’t done too much since the world got back to normal.
I keep seeing new updates in my feed and occasionally watch a video on a new feature, but trying to catch up seems intimidating. I remember learning geometry nodes when if first came out but I’m pretty sure they’ve reworked the whole thing.
I’m concerned about what I need to learn, relearn, or completely forget, in order to catch up.
What you’re looking for is called a Dolly Zoom, though it usually involves moving the camera away while zooming in (or vice versa) instead of the object size, which makes sense in traditional filmography, where the object size can’t be changed
So it’s a Gameboy Camera that harvests your data?