Texture Synthesis Using Convolutional Neural Networks — mentioned by versteegen

Sun, 21 Apr 2024 01:07:45 GMT

DNNs are very good at learning features so are a natural fit if you have lots of training data. The main drawback is then you've lost the ability to work with small data. The other drawback is the computational cost of the maxent model on top of it. So you get both the best and the worst of both halves. So: input --DNN--> feature vector --minimax_entropy_optimisation--> maxent model --sampling/inference--> output But minimax entropy learning is just learning a model that matches statistics of a set of features (filters). If you just want to draw a single sample from that model or the maximum…

Paper and discussion history. A mention is not an endorsement.

Texture Synthesis Using Convolutional Neural Networks — mentioned by arketyp

Fri, 08 Apr 2016 04:03:38 GMT

I'm guessing recent progress in texture synthesis [1] and content generation [2] using deep convolutional nets made this possible. It would be interesting to see what was actually fed into the generating system. That would be a piece of art truly speaking magnitudes. [1] http://arxiv.org/abs/1505.07376 [2] http://arxiv.org/abs/1511.06434

Paper and discussion history. A mention is not an endorsement.

Texture Synthesis Using Convolutional Neural Networks · HackerPapers discussions

Texture Synthesis Using Convolutional Neural Networks — mentioned by versteegen

Texture Synthesis Using Convolutional Neural Networks — mentioned by arketyp