You simply start drawing your best version of a pizza, or house, or dog, or birthday cake and the algorithms try to figure out what it is that you’re trying to draw. It then tries to match your squiggles with drawings in its database, and if it finds any possible matches, it’ll show them in a list at the top of your virtual canvas. If you like one of those options, you simply click on it and AutoDraw replaces your amateurish creation with something a bit slicker. — techcrunch.com
The new AutoDraw tool is part of Google's A.I. Experiments sandbox and pairs machine learning with artist drawings from a growing, crowd-sourced library. "AutoDraw’s suggestion tool uses the same technology used in QuickDraw, to guess what you’re trying to draw," states the tool's About page. "Right now, it can guess hundreds of drawings and we look forward to adding more over time."
While simplicity and intuitive accessibility are the striking features of this early version, AutoDraw—and a universe of variations—show a lot of potential for architectural sketching and prototyping.
hand sketch turns into clip art - further reduction of anything human.
I think this is impressive not as a drawing tool, but as a look into the level of image comprehension AI are capable of these days. I'd be interested to see how Google uses this tech beyond this sort of showcase app.
All 3 Comments
Yes, more cookie cutter images.
hand sketch turns into clip art - further reduction of anything human.
Id argue that this is what programs like Revit have also done...
Revit is a tool, nothing more. If you value hand sketching in architecture, Revit won't supplant it, just as this toy won't supplant a freehand style for cartoonists or other artists. Blaming Revit for the weaknesses of lazy architects is like blaming the chocolate cake for making you fat.
I agree completely, you are so confined by using revit you can't be as unique but so efficient from a money point of view
If one can't find a way to be a great designer while still using Revit, then perhaps this isn't the right profession to be in. People swore CAD was the death knell of great architecture. They were wrong then, too.
Id argue that if you are "Designing" in Revit, you were a mediocre designer to begin with.
Care to elaborate? Sounds like an overly broad statement to me. I don't claim to design in Revit, nor would it be my first choice, but I also don't preclude the possibility of someone doing so successfully.
Pete, you are an advanced revit user, as am I. You suggest anything is possible, but I don't think that is true. Simply put, Revit is limited by the tools available. There are lots of things that don't even work, for example: curves suck, a curved wall with a sloped top is junk. Compound that type of constraint by putting the tools in front of a user with limited ability and lack of desire to push the software and you get stuck with "out of the box" architecture. Sketchup was the same way - all of these buildings that were a direct result of the push pull tool and they looked like shit. I agree that you can do a lot in revit and if you push the tools to the limits, you can get some decent design, but you also need to know when to abandon ship to get the result you want and it rarely can come from a single suite of software. Think about a beginner revit user trying model ronchamp....never going to happen.
I'm fairly new to this profession and know this where I want to be. I'm proficient in revit enough to work, but understand there is still some to learn.
Beside all that, I am atristicly minded and I have
I'm fairly new to this profession and know this where I want to be. I'm proficient in revit enough to work, but understand there is still some to learn.
Beside all that, I am atristicly minded and I have
Worked for an architect that wanted me to an axonmetric section for a wooden roof that he had sketched up for me I had to tell him that revit couldn't allow me to draw it how he wanted, he got really frustrated about but ended up just sticking to what had modeled up in revit. So my question here is how can one's drawings stand out amongst revit projects, how can we be more creative and open in revit? Because I can always spot a project done in revit. Also I'm not talking about the actual finished building coming out of Revit because there is plenty of ways to take designs from Rhino or sketch up to revit and still have a unique building. It's the the finished construction sets that I'm talking about, we just need jazz them up a little bit.
Design isn't a pure process. Revit is merely a part of it. If an architect has an idea but cannot get it documented within the fee allowed, is the design complete? If an idea can't be drawn in Revit, is the design complete?
I would suggest that one should use the appropriate tools for the job. If Revit shaves hours off of door schedules, use it for that. If it cannot model that curvaceous form, find some other way. If you can get it designed using a pen and a napkin, don't even use it.
But I feel the argument that the glut of bad buildings is the fault of Revit is not defensible.
99.9% of our built environment is shit...is it revit's fault...no, but is it helping to allow architects to do more shit design faster and with less people...yes. Good design is very hard to execute in revit and shit is easy as pumpkin pie. Colin, no offense to your comment, but I would guess that your wood roof in axo is totally possible but it was your lack of training and/or skill in revit that allowed a less interesting building to leave the office and that is the point that others are trying to make...the tools controlling the design and not the designer...that is when revit and any other software fails.
Yeah I guess your right, I'm not too skilled only a year in Revit at my firm. But modeling in Revit just sucks, and that could be because I am much better in Rhino. I ended up making the model in Rhino and made it 2D and added the 2D drawing to our set and was a led to add notes and such to it. I agree that it's makes scheduling so much easier and I love that about revit.
I think this is impressive not as a drawing tool, but as a look into the level of image comprehension AI are capable of these days. I'd be interested to see how Google uses this tech beyond this sort of showcase app.
Block this user
Are you sure you want to block this user and hide all related comments throughout the site?
Archinect
This is your first comment on Archinect. Your comment will be visible once approved.