Comments (8)
Eagerly waiting for the answer
from mipnerf.
There's nothing happening in Equation 8 besides straightforward linear algebra and manipulating Gaussians. If you have a Gaussian defined along an axis (in this case, d
) with a variance along the axis of sigma_t^2 and the variance perpendicular to the axis of sigma_r^2, and you want to construct a covariance matrix in 3D, then you should "inflate" that gaussian by sigma_t^2 along the space spanned by d (which is dd^T) and you should "inflate" it in the perpendicular direction (I - dd^T, the null space of d) by sigma_r^2.
from mipnerf.
@jonbarron Does setting diag = true (use d**2 instead of dd^T) in your code mean that you believe the r and t are irrelevant?
from mipnerf.
No, it doesn't. Setting diag=true makes no assumptions, it just takes advantage of some math to compute an identical quantity a faster way.
from mipnerf.
@jonbarron I think that the coefficients of the two terms(sigma_t^2 and sigma_r^2) in formula 8(2) represent the decomposition of the vector. In the second coefficient, the unit matrix represents the vector itself, and the one that is subtracted represents the projection from the conical frustum coordinate system to the world coordinate system in the direction of the axis, so the second term can only represent the variance perpendicular to the direction of the axis. If we follow the above way of understanding, why is there a formal inconsistency between the coefficients of the first term and the subtracted coefficients of the second term (they differ by ||d||_2^2 times)? I hope you can answer my confusion, thank you very much!
from mipnerf.
i have the same question.Hope someone can solve the problem @jonbarron @KevinSONG729
from mipnerf.
If the direction is normalized, then ||d||=1.
But mipnerf used an unnormalized direction vector, which is confusing...
@jonbarron I think that the coefficients of the two terms(sigma_t^2 and sigma_r^2) in formula 8(2) represent the decomposition of the vector. In the second coefficient, the unit matrix represents the vector itself, and the one that is subtracted represents the projection from the conical frustum coordinate system to the world coordinate system in the direction of the axis, so the second term can only represent the variance perpendicular to the direction of the axis. If we follow the above way of understanding, why is there a formal inconsistency between the coefficients of the first term and the subtracted coefficients of the second term (they differ by ||d||_2^2 times)? I hope you can answer my confusion, thank you very much!
from mipnerf.
@jonbarron I think that the coefficients of the two terms(sigma_t^2 and sigma_r^2) in formula 8(2) represent the decomposition of the vector. In the second coefficient, the unit matrix represents the vector itself, and the one that is subtracted represents the projection from the conical frustum coordinate system to the world coordinate system in the direction of the axis, so the second term can only represent the variance perpendicular to the direction of the axis. If we follow the above way of understanding, why is there a formal inconsistency between the coefficients of the first term and the subtracted coefficients of the second term (they differ by ||d||_2^2 times)? I hope you can answer my confusion, thank you very much!
I think so. The non-diagonal of the covariance matrix is 0, right?
from mipnerf.
Related Issues (20)
- Why are we using cylindrical volume representation instead of conical frustum for forward facing scenes? That's because of changing camera's coordinate system to NDC? HOT 1
- Question about mipnerf360 HOT 4
- Question about CPU OOM. HOT 2
- Extracting isosurfaces of Mip-NeRF HOT 1
- Radii computation with and without NDC HOT 3
- Why positional encoding for viewing direction? HOT 3
- a bug about training process
- Why the training time is longer than NeRF HOT 4
- average error matrics in paper HOT 2
- Is it safe to use unnormalized ray directions while sampling points? HOT 3
- Tiny typo in supplemental material HOT 1
- origins and directions issues HOT 2
- scripts/train_blender.sh: line 31: 11426 Segmentation fault (core dumped)
- A confusion about the order of sin and cos in the IPE part HOT 3
- Is dx (or base_radius of cone) all the same for rays of different pixel in a picture? HOT 1
- Use normalized direction vector or not? HOT 1
- How to understand "The variance of the conical frustum with respect to its radius r is equal to the variance of the frustum with respect to x or (by symmetry) y. " HOT 4
- How to get equation (5) HOT 1
- Requirements.txt needs a dependency resolver HOT 2
- A question about the code
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from mipnerf.