Luminar NEO and Lightroom are both investing in AI-driven edge detection to mask areas precisely. Darktable v3.6 has the ability to mask based on focus detection. Have the developers contemplated adding AI-based edge detection algorithms to enhance masking?
I have ON1 and it has a lot of those features touted and they work and they donāt so you end up tweaking quite a bit ā¦they have a new sky swap but honestly when I tweak parametric masks in DT and if need be restrict or protect with a drawn mask I can mask trees building etc pretty much as well and as fast as it can get done in ON1ā¦I canāt speak to the two you mention as I donāt use themā¦
No. I donāt think anyone wants to add that.
AI is just useful if properly trained - training isnāt a job for just a few developers spending some spare time
NLP and object recognition require large sets of training files, but edge detection is by now an easy method to integrate. GIMP already has 5 methods for edge detection that require no training files.
then thats not AI
The new version of Lightroom separates faces with hair in one click and it is AMAZING.
Advances in software quickly become the norm. Most of us by now can run Lightroom or Luminar in docker containers at close to bare metal speeds on Linux. Darktable should not lag behind.
you might compare the size of adobes developer team and the darktable team - but of course you can join the team an do all that fancy stuff.
I think this is a classic case of people āexpectingā or āwantingā software to go a certain way, but I have a feeling - because I canāt know for sure - that the developers simply donāt want to invest their time in that.
Itās open source, people code what they want to code. If the few DT devs donāt want to do it, they donāt want to do it. But maybe they do? Itās not like every coder in the planet is suddenly an AI-algorithm-expert.
If someone somewhere starts working on it and contributes, Iām sure they will not refuse it.
Darktable only lags in marketing. Parametric and drawn masks have made the selections I want to make relatively easy. The selections that Iāve made that took me a while arenāt going to be solved by AI.
Again, someone has to code the stuff, train the model, and keep it updated. Unless youāre going to do that, I donāt really see it happening.
And they probably had a 100 guys and a million(s) dollar budgetā¦ā¦ just for that one feature
Selecting faces is easy with Neural Net methods IF you are satisfied to find a bounding box.
Selecting a pixel perfect bound around the face is extremely difficult and requires both a ton of properly labeld training data (where exactly is the pixel boundry between a face and itās surrounding?) and lots of expensive compuation power to really train the netā¦
I just saw a video someone made raving about the new adobe masking yet when they used select person, the person was holding a string of balloons and all those were selectedā¦no person has that shape so I am not sure how āAIā it even isā¦ I think like all these toolsā¦some test images will give a perfect result and others will notā¦
ā¦and then the problem (as with a lot of āuser friendlyā software) is thereās nowhere to turn when the āintelligenceā is dumb. Perhaps theyāll provide a āmensaā version for extra money.
Maybe all the āexpertsā here should try the software in question before throwing up NIH vomit.
And you should not be so salty when you donāt get the answers you want.
Steven I donāt have the software and you doā¦so really I canāt comment from an informed positionā¦But I have seen a few videoās for example this one
and this one
In the first video select subject selected a rock and some sky in addition to the person. Later the way the skin was masked was not particularly AIā¦but this might not be what you are talking about.
In the second video the presenter used the select subject on a black monkey that should have been easy to maskā¦it missed his rather large tailā¦selected the branch he was on and missed his handā¦more over the presenter keeps saying how amazing it is and doesnāt even acknowledge a pretty obvious artifactā¦The sky that he chose to mask would have easily been done by any software with a luminosity maskā¦so he didnāt push itā¦
So its fair to say I donāt have the software and should not really comment. You do have it so you would be a better judgeā¦but from many of the examples I see LR still has a lot of work to do and I have not seen a demonstration as clearly perfect as you mentioned. There seem to be a lot of artifacts that still need corrected and actually it makes me more impressed about how good the DT parametric masking is for a FOSS tool compared to a 305B dollar company.
Still I think your question has meritsā¦are there areas that DT could improve masking and what would those beā¦given the software is written by people doing things that interest them as opposed to individuals paid to make a product for a consumerā¦what might those beā¦
The answer might come from a use case analysis rather than a comparison of what another software can doā¦so right now are there limitations to masking in DT that are holding people back or could be improved or made easierā¦some input from users towards that end might direct where any new improvements to DTās masking might be focused going forward.
I encounter images where I know an edge must exist, but no local processing can detect it because the pixels from two objects have the same character. Using human intelligence looking at the area around the problem, I can see the photograph has two objects, and some areas show a clear edge, and for some pixels I can mentally assign them to one object or the other. By continuing clear edges into the problem area, I can choose an arbitrary line for an invented edge that may not be accurate but is credible.
So I can see that, in principle, AI could solve these cases. But I donāt have enough AI experience to design or implement this, or even estimate how much work by humans or computers might be needed, or how good the results would be.
That is an excellent pointā¦here is the example from the video that the presenter raved about and you can see the subject is quite different from the background to that part should be easy but the the tree introduces a block to the algorithm when it processes the pixels and it misses the tail and the left hand of the monkeyā¦and it includes the branch he is sitting on