Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Lepton image compression: saving 22% losslessly from images at 15MB/s

blogs.dropbox.com

Post reply on HN
Print view View original

141–150 of 196 posts

Re: Lepton image compression: saving 22% losslessly from images at 15MB/s

#141

Post by sapphireblue »

Stanleyc23 wrote: post #134
joeyo wrote: post #131

Earlier quoted context omitted.

Absolutely, yes. There is a very deep link between compression and "understanding". I think we have every reason to believe that networks that can understand/"explain away" the content/statistics of a scene ought to be able to compress them better. I presume someone (or likely many people) are working on exactly this.

Very cool! if anyone who comes across this particular thread knows about papers/research being written about this topic, I'd be very interested to learn more.

There is an award-winning compressor that uses many statistical models (and a 3-layered dense neural network) to compress the data losslessly: http://www.byronknoll.com/cmix.html

Also there is a free book that contains descriptions of various common and exotic compression formats http://www.mattmahoney.net/dc/dce.html

Overall I think we are yet to see the full potential of deep learning unleashed on data compression. For example the neural network in cmix compressor is quite primitive compared to modern architectures. Someone will certainly find a way to do better than that!

Re: Lepton image compression: saving 22% losslessly from images at 15MB/s

#142

Post by sapphireblue »

Stanleyc23 wrote: post #126

Just a random idea: could machine learning algorithms that do object recognition help to improve the compression of images or videos? Maybe a lossy algorithm could compress away "irrelevant" things. This way a high resolution frame might have lower resolution objects inside but it would he ok because the important part of the content is preserved.

Autoencoders are a long known approach to use neural networks for lossy compression. Some papers about using these models as aids for compression are googleable.

Re: Lepton image compression: saving 22% losslessly from images at 15MB/s

#143

Post by unexistance »

colechristensen wrote: post #30
ausjke wrote: post #21

This is very impressive for archiving images. For a quick test, I run it over ~1.3GB JPEG pictures I had locally, the finally result is 810M, that's 66% of the original size, very impressive considering it's lossless. It only deals with jpg file though, no png, no iso, no zip, no any formats other than JPG. If someone can do this over video files that will be PiedPiper comes into real life.

The reason this can be done with JPEGs is the compression hasn't been updated. There are folks that have used h264 for compressing images and webp uses vp8 compression, both with much better results than JPEG. Lepton is cool because it helps make existing technology a whole lot better, but what we actually need is a better image format. You wouldn't see the same leap for videos because people have been working hard t…

perhaps BPG is better? By the great Fabrice Bellard

http://bellard.org/bpg/

Re: Lepton image compression: saving 22% losslessly from images at 15MB/s

#144

Post by CarVac »

eon1 wrote: post #130
e12e wrote: post #120

Earlier quoted context omitted.

The size difference between "high quality" jpeg and lossless compressed TIFFs can be quite significant - so I it might not be feasible to use eg. TIFF for archiving. And jpegs might very well be "good enough". Eg. just tested on a small 10MP Sony ARW raw image - the raw file is 7MB, the camera jpeg is 2.3MB, and a tiff compressed with LZW is 20MB (uncompressed 29MB). The raw tiff run through lzma is 9.3MB. But either…

How on earth did a 7MB raw blow out to a 20MB TIFF? Isn't that going from uncompressed RGBG to losslessly compressed RGB?

Raw files store only one channel per pixel. A TIFF has been demosaiced and stores 3 channels per pixel.

On top of that, most sensible raw formats only store 12 or 14 bits per pixel, instead of 16.

And then most are compressed, some losslessly and some lossily (like the infamous Sony format that packs it down to an average of 8 bits per pixel but does exhibit artifacts).

Re: Lepton image compression: saving 22% losslessly from images at 15MB/s

#145

Post by kalleboo »

unexistance wrote: post #143
colechristensen wrote: post #30

Earlier quoted context omitted.

The reason this can be done with JPEGs is the compression hasn't been updated. There are folks that have used h264 for compressing images and webp uses vp8 compression, both with much better results than JPEG. Lepton is cool because it helps make existing technology a whole lot better, but what we actually need is a better image format. You wouldn't see the same leap for videos because people have been working hard t…

perhaps BPG is better? By the great Fabrice Bellard http://bellard.org/bpg/

BPG is based on h265

Re: Lepton image compression: saving 22% losslessly from images at 15MB/s

#147

Post by colechristensen »

manigandham wrote: post #119
colechristensen wrote: post #30

Earlier quoted context omitted.

The reason this can be done with JPEGs is the compression hasn't been updated. There are folks that have used h264 for compressing images and webp uses vp8 compression, both with much better results than JPEG. Lepton is cool because it helps make existing technology a whole lot better, but what we actually need is a better image format. You wouldn't see the same leap for videos because people have been working hard t…

Yes, it should all just switch to FLIF http://flif.info/

What are the processing implications?

The lack of processing comparisons raises that question pretty loudly, and it's definitely important in a mobile world. There's more to performance than size

Re: Lepton image compression: saving 22% losslessly from images at 15MB/s

#148

Post by pierrec »

mahyarm wrote: post #105
randyrand wrote: post #90

Earlier quoted context omitted.

IMO, it shows how they don't plan to make any money from this, don't consider it a large competitive advantage, and think that the largest advantage of open sourcing it are the 'free' open source volunteers will improve the software. It's interesting that they don't consider it a large enough competitive advantage. Either that or they are using this to attract engineers.

You also open source if it's in your best interest for something to become the 'standard'. In google there is a regret that they didn't open source a lot of stuff, because it ends up being reproduced outside of google in some form. The open source companies have an advantage in hiring and overall advancement of their product by using the open source version whatever their internal version was. You also see it in face…

Wait, since when is Facebook pushing for Haxe? I tried looking it up, but I'm not finding much. It would be really cool (I love Haxe). But I'm guessing you only went a bit over the top with that particular example.

Re: Lepton image compression: saving 22% losslessly from images at 15MB/s

#149

Post by jmspring »

There were techniques discussed as part of the JPEG-2000 efforts where just reordering coefficients before doing the entropy coding would gain you a good deal of compression (though at the expense of the block based nature of JPEG).

It's always good to see new techniques out in the open.

Re: Lepton image compression: saving 22% losslessly from images at 15MB/s

#150

Post by eon1 »

sevenless wrote: post #82

I'm interested in a 'super lossy' (deep learning based?) compression. You should be able to compress movies down to a screenplay and a few stage directions. A picture should of course be worth 1000 words.

Sounds a bit similar to the fractal compression experiments[0][1] that were eventually repurposed in stuff like Perfect Resize. IIRC, it worked a bit like RLE, but by generating an IFS on the fly that could be used to recreate the image, instead of just storing pixel sequences.

[0] http://www.cs.northwestern.edu/~agupta/_projects/image_proce...

[1] http://www.math.psu.edu/tseng/class/Fractals.html

Post reply on HN