jcs Posted July 25, 2017 Share Posted July 25, 2017 While fractal and wavelet compression made a splash a few years ago (and wavelet is still used today in JPEG2000 and Redcode RAW), there's a lot more to be discovered based on generative mathematics and machine learning. Here's one cool example: http://www.wave.one/icml2017/ Quote Link to comment Share on other sites More sharing options...
ntblowz Posted July 26, 2017 Share Posted July 26, 2017 interesting link, will it make video file size even much smaller? Quote Link to comment Share on other sites More sharing options...
jcs Posted July 26, 2017 Author Share Posted July 26, 2017 Yeah, generative compression applied to moving images (video) will result in a massive reduction in file sizes vs. the current macroblock DCT methods. Quote Link to comment Share on other sites More sharing options...
Eric Calabros Posted July 26, 2017 Share Posted July 26, 2017 But 0.08 bit per pixel is around 20Mb/s for 4k@30. I'm sure h.265 is already producing a pretty clear image at this data rate. Quote Link to comment Share on other sites More sharing options...
jcs Posted July 26, 2017 Author Share Posted July 26, 2017 2 hours ago, Eric Calabros said: But 0.08 bit per pixel is around 20Mb/s for 4k@30. I'm sure h.265 is already producing a pretty clear image at this data rate. That would be using all I-frames (no compressed motion deltas). To really leapfrog H.265, they've got to apply the generative encoding concept to inter-frame compression. A hybrid concept would be to use generative encoding for I-frames, and use concepts from H.265 for inter-frame encoding. Quote Link to comment Share on other sites More sharing options...
Recommended Posts
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.