5 votes

Image-in image-out neural network architectures

I think the second approach will be the best because it only requires that your training set is annotated with four labels for each of the four corners of the paper sheet. This is sort of the idea of ...
user avatar
  • 179
4 votes
Accepted

Other deep learning image generation techniques besides GANs?

There are several generative models that have been proposed before or roughly at the same time of the GAN (2014). For example, the deep Boltzman machine (2009), deep generative stochastic network (...
user avatar
  • 34.4k
3 votes

What are the fundamental differences between VAE and GAN for image generation?

GANs generally produce better photo-realistic images but can be difficult to work with. Conversely, VAEs are easier to train but don’t usually give the best results. I recommend picking VAEs if you ...
user avatar
3 votes
Accepted

What kind of algorithm is used by StackGAN to generate realistic images from text?

The paper StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks should provide the answers to your questions. Here's an excerpt from the abstract of the paper. ...
3 votes
Accepted

beautify an image with reinforcement learning

The purpose of Reinforcement Learning is to maximize some notion of cumulative reward, leading me to the point (1) : as far as I understand, there is no timesteps in your problem and the "reward" is ...
user avatar
  • 266
2 votes

Algorithm that creates new images based on other images

I'm not an expert on that so you could probably get a better answer. I'm not sure to understand what you're looking for. Are the couple of images about the same thing? Like pictures of cats and you ...
user avatar
  • 21
2 votes
Accepted

Does MMD-VAE solve the problem of blurred images of vanilla VAEs?

[Answering my own question after 5 months of studying VAE models] The point of the MMD-VAE or InfoVAE is not exactly to emphasise on the visual quality of generated samples. It is to preserve greater ...
user avatar
  • 128
2 votes
Accepted

What makes GAN or VAE better at image generation than NN that directly maps inputs to images

The only disadvantage and difference between these generative models and the method you describe, is the input. You describe inputting tags, where as for a GAN, or VAE, the generation segment of the ...
user avatar
  • 1,246
2 votes

Image-in image-out neural network architectures

You could try U-Net for approach 1. This is called the image-to-image translation problem in machine learning. You could see more architectures in this paper: https://arxiv.org/pdf/2101.08629.pdf
user avatar
2 votes
Accepted

What does "Gau" in GauGAN stand for?

As you know, GauGAN is the following (from this post): GauGAN was a Microsoft Paint-style platform that let uses create landscape images, with the model then able to turn them into photorealistic ...
user avatar
  • 1,663
2 votes

Best architecture to learn image rotation?

This would likely suffer from the blurry image problem that autoencoders are known to suffer from. See also here. On the other hand, using GAN's to sharpen your images doesn't seem particularly ...
user avatar
  • 261
1 vote

Are there some known neural networks that, given an input image, can generate a similar image, with the same topic?

The closest literature to what you're suggesting is indeed related to GANs, specifically to arithmetic performed on the latent space learned by generators. Check Unsupervised Representation Learning ...
user avatar
1 vote

What is the state-of-the-art algorithm for neural style transfer?

So for neural style transfer, using the particular method described in Gatys paper, nobody has done better than using VGG net. This is seemingly due to VGGs inherent stability and inability to learn ...
user avatar
  • 11
1 vote

How can I generate unique random patterns (similar to the ones in Nutella jars)?

Some excerpts from Nutella 'Hired' an Algorithm to Design New Jars. And It Was a Sell-Out Success: The "algorithm" is called HP Mosaic and is included free in HP SmartStream Designer for HP ...
user avatar
1 vote

Is it feasible to use GAN for high-quality image synthesis other than human faces?

I'd challenge your assertion somewhat that the generated images of other categories are of much worse quality than the faces! Take the bikes on transparent / solid backgrounds they look great! Where ...
user avatar
  • 880
1 vote

Is it feasible to use GAN for high-quality image synthesis other than human faces?

Generative Adversarial Networks, basically boil down to a combination of a generic Generator and a Discriminator trying to beat each other, so that the generator tries to generate much better images (...
user avatar
1 vote
Accepted

What is the name of the method for the smart extend of image surroundings?

In computer vision, the problem of filling missing parts of an image is called image inpainting; the subtask of filling the surroundings is called image outpainting in [1], which is your problem. The ...
user avatar
  • 34.4k
1 vote

Is the range of inception score flexible or bounded based on number of classes?

Yes. You are right. The IS is bound by the number of classes. This paper titled "A Note on the Inception Score" clearly shows a formal proof of the same. Please head to section 3.3 of the ...
user avatar
  • 238
1 vote

Is there any metric for calculating how natural a single image is given a dataset of the same class images?

Evaluating synthetically generated images is challenging and an active area of research. The problem is that the "how natural is an image"-task is not well-defined and subjective. To ...
user avatar
1 vote

What dataset might Elon Musk's Dall-E have used?

DALL·E is a 12-billion parameter version of GPT-3 trained to generate images from text descriptions should be the same data they used to train the GPT-3
user avatar
  • 111
1 vote

What algorithm would you advise me to use for my task?

Assuming that the image is blank everywhere but where the face is drawn... The first step is to scale the image to the mask. That doesn't require a detailed explanation here as it is too trivial a ...
user avatar
1 vote

Can you give me a piece of advise of the network sructure that would be suitable for my task?

Just use IMGAug library for Applying the 'zoom' augmentation on the images and a convnet (or even MLP) would have no problem in this task. Zooming on the image ...
user avatar
  • 126
1 vote

Can you give me a piece of advise of the network sructure that would be suitable for my task?

Instead of NNs, you can use RANSAC algorithm to calculate homography matrix, but first you need to find feature points. However, if your images are blob-like, you may not get such a successful results....
user avatar
  • 174
1 vote

What makes GAN or VAE better at image generation than NN that directly maps inputs to images

I will only focus on the VAE because I am more familiar with it, but the explanations may also apply to the GAN and other generative models. In the case of the VAE, you train a neural network not ...
user avatar
  • 34.4k
1 vote

Context-based gap-fill face posture-mapper GAN

I believe you may want to use a Sum Product Network for this task. SPNs are the state-of-the-art approach for face completion, and there are several more recent papers on this topic since the original ...
user avatar
1 vote

How to generate the original image from feature set?

The model (that I know of) which most resembles your description is the auto-encoder, which is trained to learn a compact representation (a vector) of the input, which can later be used to reconstruct ...
user avatar
  • 34.4k
1 vote
Accepted

Creating videos of AI generated photographs

I wouldn't really consider what they are doing as AI - they are using a script that intelligently overlaps various images of existing people in order to create a new face. Animating those images isn'...
user avatar
  • 136

Only top scored, non community-wiki answers of a minimum length are eligible