reconstruction | 3D reconstruction with openCV and SFM | 3D Printing library

Following my previous question , I have written this code to train an autoencoder and then extract the features. (There might be some changes in the variable names)

• I'm have studied about Autoencoder and tried to implement a simple one.
• I have built a model with one hidden layer.
• I Run it with mnist digits dataset and plot the digits before the Autoencoder and after it.
• I saw some examples which used hidden layer of size 32 or 64, I tried it and it didn't gave the same (or something close to) the source images.
• I tried to change the hidden layer to size of 784 (same as the input size, just to test the model) but got same results.

What am I missing ? Why the examples on the web shows good results and when I test it, I'm getting different results ?

I am writing an ARKit app where I need to use camera poses and intrinsics for 3D reconstruction.

The camera Intrinsics matrix returned by ARKit seems to be using a different image resolution than mobile screen resolution. Below is one example of this issue

Intrinsics matrix returned by ARKit is :

[[1569.249512, 0, 931.3638306],[0, 1569.249512, 723.3305664],[0, 0, 1]]

whereas input image resolution is 750 (width) x 1182 (height). In this case, the principal point seems to be out of the image which cannot be possible. It should ideally be close to the image center. So above intrinsic matrix might be using image resolution of 1920 (width) x 1440 (height) returned that is completely different than the original image resolution.

The questions are:

• Whether the returned camera intrinsics belong to 1920x1440 image resolution?
• If yes, how can I get the intrinsics matrix representing original image resolution i.e. 750x1182?

I have been asking several questions for locating and extracting maze from photos on SOF, but none of the answers I get work across different photos, not even across 4 testing photos. Every time when I tweaked the code to make it work for 1 photo, it will fail on the rest of photos due to warped corners/parts or light etc. I feel that I need to find a way which is insensitive to warped image and different intensity of light or the different colors of maze walls(the lines inside a maze).

I have been trying to make it work for 3 weeks without a luck. Before I drop the idea, I would like to ask is it possible to just use Image Processing without AI to locate and extract a maze from a photo? If yes, could you please show me how to do it?

Here are the code and photos:

I wrote a full working example for both nfft, and scipy.fft. In both cases I start with a simple 1D sinusoidal signal with a little noise, take the fourier transform, and then go backwards and reconstruct the original signal.

Here is my code as clean and readable as I could manage:

I have implemented a variational autoencoder with the Keras implementation as an example (https://keras.io/examples/generative/vae/). When plotting the training loss I noticed that these were not the same as displayed in the console. I also saw that the displayed loss in the console in the Keras example was not right considering total_loss = reconstruction_loss + kl_loss.

Is the displayed loss in the console not the total_loss?

My VAE code:

I'm working on the signal compression and reconstruction with VAE. I've trained 1600 fragments but the values of 1600 reconstructed signals are very similar. Moreover, results from same batch are almost consistent. As using the VAE, loss function of the model contains binary cross entropy (BCE) and the output of the train model should be located between 0 to 1 (The input data also normalized to 0~1).

VAE model(LSTM) :

I'm a Computer Engineering student at Baskent University(Turkey,Ankara).

Can i use matlab k-wave toolbox codes in visual studio via like importing or creating the library or something, I need to know that for my Gradutation Project.

For example :

I'm trying to train an autoencoder, with constraints that force one or more of the hidden/encoded nodes/neurons to have an interpretable value. My training approach uses paired images (though after training the model should operate on a single image) and utilizes a joint loss function that includes (1) the reconstruction loss for each of the images and (2) a comparison between values of the hidden/encoded vector, from each of the two images.

I've created an analogous simple toy problem and model to make this clearer. In the toy problem, the autoencoder is given a vector of length 3 as input. The encoding uses one dense layer to compute the mean (a scalar) and another dense layer to compute some other representation of the vector (given my construction, it will likely just learn an identity matrix, i.e., copy the input vector). See the figure below. The lowest node of the hidden layer is intended to compute the mean of the input vector. The rest of the hidden nodes are unconstrained aside from having to accommodate a reconstruction that matches the input.

The figure below exhibits how I wish to train the model, using paired images. "MSE" is mean-squared-error, although the identity of the actual function is not important for the question I'm asking here. The loss function is the sum of the reconstruction loss and the mean-estimation loss.

I've tried creating (1) a tf.data.Dataset to generate paired vectors, (2) a Keras model, and (3) a custom loss function. However, I'm failing to understand how to do this correctly for this particular situation.

I can't get the Model.fit() to run correctly, and to associate the model outputs with the Dataset targets as intended. See code and errors below. Can anyone help? I've done many Google and stackoverflow searches and still don't understand how I can implement this.