News for hackers. Stuff that matters.
Re:Nvidia Vid2vid: High-resolution photorealistic video-to-v... by sjwright on Saturday September 22, 2018 @05:14AM (#18045210)
The vast bulk of Adobe's advantage is in UX, not technical algorithms. Which makes perfect sense because that tends to be the case with most F/OSS software—technically brilliant but with an face only a programmer could love.

Yes, Adobe do have some remarkable algorithms that would be difficult to replicate (e.g. heal brush and content aware fill) but these are a small minority of Adobe's software advantage.

The one that irritates me the most is vector drawing programs: open source programs (and even paid competitors) just can't touch Adobe Illustrator for the sort of work I do. I'm sure at least 50 percent of it is familiarity and muscle memory, but I've desperately tried switching to a few different options like Inkscape or Affinity and left wildly disappointed.

Re:Nvidia Vid2vid: High-resolution photorealistic video-to-v... by have_faith on Monday September 24, 2018 @05:04AM (#18056071)
You're right that UX is one of the biggest problems they have. One thing that is also hard to replicate it how well Adobe's software works together. Embedding smart objects and illustrator files in photoshop documents, right clicking a clip in Premiere and sending it to After Affects and back again without rendering an intermediate file etc.

I would be interested in a Lightroom alternative if anyone can recommend one though.

Re:Nvidia Vid2vid: High-resolution photorealistic video-to-v... by homarp on Saturday September 22, 2018 @06:21AM (#18045381)
for content aware fill and heal brush both GMIC ( https://patdavid.net/2014/02/getting-around-in-gimp-gmic-inp...) and resynthetizer ( http://www.logarithmic.net/pfh/resynthesizer ) are working quite OK.
Re:Nvidia Vid2vid: High-resolution photorealistic video-to-v... by throwaway2048 on Saturday September 22, 2018 @11:19AM (#18046317)
Gimp even had content aware fill first, It was based on a SIGGRAPH paper iirc.
Re:Nvidia Vid2vid: High-resolution photorealistic video-to-v... by deltron3030 on Saturday September 22, 2018 @06:50AM (#18045457)
Do you use the Astute plugins for AI, or the native pen tool? Affinity feels different, maybe less precise, but the functionality was way better compared with the native Adobe tool. You should try Figmas pen tool, I like it.
Re:Nvidia Vid2vid: High-resolution photorealistic video-to-v... by sjwright on Saturday September 22, 2018 @08:38AM (#18045747)
My uses are relatively trivial- logo design, SVG generation, basic layout work and PDF tinkering. My main need is fine control of beziers with auto-guides to ensure consistency.