-
Just noting that this here is quite inefficient: It would be more efficient to compute the row echelon form for as many columns as we need and extracting the information on the linearly independent co…
-
Hi, thanks for your novel work, and I'm confused about how to calculate the last Jacobian. For example, in the class HaarDownsampling, the Jacobian is calculated as follows,
` if not rev:
…
-
Hi, Thanks for sharing this excellent work! I'm trying to generate corresponding flat and warped images with forward transformation grid. Are there any way to get backward grid that recovering generat…
-
Given a model and a set of feasible transformations on that model we can define a random walk on the class of all models. We should implement that and write some Monte Carlo algorithms over models
-
Hi,
Pdpipe is marvelous, very nice tool!
One addon possibility that I was wondering:
In case of time series, de-trending is a common operation, done by taking the first differential of the data…
-
#### Summary:
Provide function to constrain a vector to the space of coefficients of stationary autoregressive functions and invertible moving-average functions.
#### Description:
When estimating AR…
-
### 🚀 The feature
The [Modified Discrete Cosine Transform (MDCT)](https://en.wikipedia.org/wiki/Modified_discrete_cosine_transform) is a perfectly invertible transform that can be used for featur…
-
## Expected Behavior
I would expect `EstimateRigidTransformation` to always give invertible affine transformations. In the case of `TransformationEstimation3Point` I would expect the linear part o…
-
In figure2 of your paper,you show K=2 is the better choice of K,so is there any different of your model with Glow when K=2? And when k=4 or 6,what's the result of inverse dynamic linear transformation…
-
It's better to have `Projective` transformation to `ImageTransformations.jl`.
```julia
# Definition of projective transformation
"""
Projective transformation.
"""
struct Projective >I feel th…