Re:Opus 1.5 released: Opus gets a machine learning upgrade
by WithinReason on Monday March 04, 2024 @06:15PM
(#39597456)
Someone should add an ML decoder to JPEG
[ Parent
| on HN ]
Re:Opus 1.5 released: Opus gets a machine learning upgrade
by viraptor on Monday March 04, 2024 @07:02PM
(#39597757)
You can't do that much on the decoding side (apart from the equivalent of passing the normally decoded result through a low percent img2img ML)
But the encoders are already there: https://medium.com/@migel_95925/supercharging-jpeg-with-mach... https://compression.ai/
Re:Opus 1.5 released: Opus gets a machine learning upgrade
by WithinReason on Monday March 04, 2024 @07:05PM
(#39597785)
You can more accurately invert the quantisation step
Re:Opus 1.5 released: Opus gets a machine learning upgrade
by viraptor on Monday March 04, 2024 @07:21PM
(#39597896)
You can't do it more accurately. You can make up expected details which aren't encoded in the file. But that's explicitly less accurate.
Re:Opus 1.5 released: Opus gets a machine learning upgrade
by adgjlsfhk1 on Monday March 04, 2024 @08:23PM
(#39598306)
If the encoders know what model the decoders will be running, they can improve accuracy. You could pretty easily make a codec that doesn't encode high resolution detail if the decoder NN will interpolate it correctly.
Re:Opus 1.5 released: Opus gets a machine learning upgrade
by viraptor on Tuesday March 05, 2024 @12:16AM
(#39599698)
That's changing the encoder and sure, you could do that. But that's basically a new version of the format. It's not the JPEG we're using anymore + ML in decoder. It's JPEG-ML on both the encoder and decoder side. And with the speed that we adopt new image formats... That's going to take ages :(
Re:Opus 1.5 released: Opus gets a machine learning upgrade
by samus on Tuesday March 05, 2024 @03:14AM
(#39600632)
That makes sense if the goal is lossless compression. Since JPEG is lossy, it is sufficient to consider the Pareto front between quality, compressed size, and encoding/decoding performance.