# What is a "canonical space"?

I am reading the paper on 3D reconstruction, ViSER: Video-Specific Surface Embeddings for Articulated 3D Shape Reconstruction, and I encountered the term "canonical space".

What is a "canonical space"? Is it widely used? Is there other use of the term?

In my understanding, a canonical space is a standard, norm space. And we want to convert sample points into that space so that we can perform standard procedures. But I don’t know if that interpretation is correct or not. And I am also interest if it is a common term or very few people use it.

• The term "canonical" pops up several times in computer vision. You could check e.g. the book "Multiple View Geometry in Computer Vision, Second Edition" for more details. I would need to read the paper to understand what they really mean by "canonical space" in that context (maybe later).
– nbro
Commented May 30, 2022 at 8:58

When they refer to canonical space, they are referring to vectors & surfaces of R^3xN.

And so canonical just means standard basis vectors.

Which are a set of linearly-independent (at right angles) vectors. for instance in R^3, [1,0,0], [0,1,0], [0,0,1] are basis vectors because

When speaking of a coordinate space:

1. they are all independent (can't be expressed as a combination of the others)
2. filled with either 0 or 1s
• Please, don't provide screenshots. Copy and paste the actual relevant text (and provide a reference to the original).
– nbro
Commented Jun 4, 2022 at 7:45