Subpixel: A subpixel convolutional neural network implementation with Tensorflow
1–10 of 47 posts
Re: Subpixel: A subpixel convolutional neural network implementation with Tensorflow
#2So, basically, this is the thing in a crime detective movie where the forensic analyst is looking at a terrible pixelated surveillance camera still and says "enhance," and the computer magically increases the resolution to reveal the culprit's face.
Just another entry on the "things that are supposed to be impossible that convolutional nets can do now."
Re: Subpixel: A subpixel convolutional neural network implementation with Tensorflow
#3So, basically, this is the thing in a crime detective movie where the forensic analyst is looking at a terrible pixelated surveillance camera still and says "enhance," and the computer magically increases the resolution to reveal the culprit's face. Just another entry on the "things that are supposed to be impossible that convolutional nets can do now."
yup, to certain point! there are information theoretic limits though. You can fill in information, but there will be biases to a certain point. in this case defined by the dataset. if the "enhance" is too strong, we should be careful with what we do with the results in forensics.
but man, it can make your internet pics look smooth! :) thanks for the comment!
Re: Subpixel: A subpixel convolutional neural network implementation with Tensorflow
#4Interesting image "upscale" algorithm.
I'm not familiar enough with the field to understand how the "neutral net" part feeds in, other than to do parallel computation on the x-pos, y-pos, (RGB) color-type-intensity tensor interpolated/weighted into a larger/finer tensor.
(linear algebra speak for upscaling my old DVD to HD, that sort of thing)
At the risk of exposing my ignorance, this has nothing to do with "AI", right? It's "just" parallel computation?
Re: Subpixel: A subpixel convolutional neural network implementation with Tensorflow
#5ENHANCE. ENHANCE.
Re: Subpixel: A subpixel convolutional neural network implementation with Tensorflow
#6Interesting image "upscale" algorithm. I'm not familiar enough with the field to understand how the "neutral net" part feeds in, other than to do parallel computation on the x-pos, y-pos, (RGB) color-type-intensity tensor interpolated/weighted into a larger/finer tensor. (linear algebra speak for upscaling my old DVD to HD, that sort of thing) At the risk of exposing my ignorance, this has nothing to do with "AI", ri…
yeah, no AI. Its low level computer vision. There is no implicit understanding of the scene to enhance it here. We show the neural nets several examples of low and high quality images it learns a function that makes the low quality looks more like the high quality.
this may make you feel disappointed now, but in the write up we are also pitching this same module to be used in generative networks and other models that do build an understanding of the scene. Lets see what the community (and ourselves) can do next...
Re: Subpixel: A subpixel convolutional neural network implementation with Tensorflow
#7So, basically, this is the thing in a crime detective movie where the forensic analyst is looking at a terrible pixelated surveillance camera still and says "enhance," and the computer magically increases the resolution to reveal the culprit's face. Just another entry on the "things that are supposed to be impossible that convolutional nets can do now."
yup, to certain point! there are information theoretic limits though. You can fill in information, but there will be biases to a certain point. in this case defined by the dataset. if the "enhance" is too strong, we should be careful with what we do with the results in forensics. but man, it can make your internet pics look smooth! :) thanks for the comment!
If you have multiple images of the same scene (for example, from video frames), you should be able to use information across frames for a true enhancement?
Re: Subpixel: A subpixel convolutional neural network implementation with Tensorflow
#8ENHANCE. ENHANCE.
Re: Subpixel: A subpixel convolutional neural network implementation with Tensorflow
#9I'm not sure, but there seems to be something wonky in the input images. They are very blocky, so I thought that they would be just pixel doubled (or quadrupled) from low-res pictures, but the blockiness lacks the regularity I'd expect from pixel-doubled images.
How were the input images prepared?
Re: Subpixel: A subpixel convolutional neural network implementation with Tensorflow
#10Earlier quoted context omitted.
yup, to certain point! there are information theoretic limits though. You can fill in information, but there will be biases to a certain point. in this case defined by the dataset. if the "enhance" is too strong, we should be careful with what we do with the results in forensics. but man, it can make your internet pics look smooth! :) thanks for the comment!
If you have multiple images of the same scene (for example, from video frames), you should be able to use information across frames for a true enhancement?
;) sshh! don't say that too loud yet. but, remember our names...