Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > comp.compression > #4006

Re: Neural Image Compression

Show all headers | View raw

In comp.compression, Justin Tan  <justin.tan@coepp.org.au> wrote:
> I'd like to share a side project I worked on which generalizes transform
> coding to the nonlinear case. Here the transforms are represented by
> neural networks, which learn the appropriate form of the transform. The
> result of the transform is then quantized using standard entropy coding.
> 
> Github: https://github.com/Justin-Tan/high-fidelity-generative-compression
> Interactive Demo:
> https://colab.research.google.com/github/Justin-Tan/high-fidelity-generative-compression/blob/master/assets/HiFIC_torch_colab_demo.ipynb
> 
> There are some obvious shortcomings to this method - such as, that it
> only caters for image data, cannot be adjusted to attain a variable
> bitrate, short of training a different model, and is unrealistically
> slow for practical applications.

Also:

   Clone repo and grab the model checkpoint (around 2 GB). 

If you need 2GB of data around to compress / decompress images, you need
a lot of images before this starts "winning".

> I'm not a traditional compression expert, so would appreciate any
> insight about the deficiencies of this method from those who are. Note
> this is not my original idea and is a reimplementation.

I'm no expert in compression, I just read this group for the occasional
insight.

Elijah
------
particularly interested in image compression

Back to comp.compression | Previous | Next — Previous in thread | Find similar | Unroll thread

Thread

Neural Image Compression Justin Tan <justin.tan@coepp.org.au> - 2020-09-20 21:29 -0700
  Re: Neural Image Compression Stephen Wolstenholme <steve@easynn.com> - 2020-09-21 15:45 +0100
  Re: Neural Image Compression Eli the Bearded <*@eli.users.panix.com> - 2020-09-21 17:50 +0000

csiph-web