News for hackers. Stuff that matters.
Re:Show HN: Neural Image Compression Demo by tonic_section on Saturday September 12, 2020 @03:31PM (#24454870)
Yeah, high frequency detail such as facial features for faraway figures or text tend to get washed out after compression - this is probably due to a couple reasons: 1) The training dataset contains relatively few pictures including text, 2) high-frequency detail is too expensive to encode and the model learns to forgo encoding this in favor of more 'important' features such as shapes, colors, etc.

There are no comments on this comment yet.