Thanks for the reference. Are you aware of any (commercially available) handdrawing to CAD software? I need to do a bunch of relatively simple figures for my thesis, and it would be much easier if I could just use handdrawings and than transform them to professionaly looking figures.
Have you tried Google SketchUp? It might be the closest thing to this type of ease-of-use that I've seen so far, and it's free.
Thanks, will try it out, but wrom tutorial vids it looks more on the CAD side than handdrawing side.
WOW. Forget the Photoshop stuff, this needs to be integrated with 3D printing immediately . Spit out a design file into Tinkercad[1] for some minor adjustments and BAM, you've made a printable 3D model. [1] https://tinkercad.com/
That's what I thought when I saw it. Break something, take a quick snap and import it, fix the damage, send to printer. Very little 3d modelling skill required, making it way more accessible to the average person.
A lot of cool rendering/modeling research seems amazingly well-suited for the film industry and this is a perfect example ... besides the obvious applications in making CGI versions of real-world scenes, you can just imagine the director saying "oh no, that lamp is in the wrong location in all that footage... move it (without reshooting)!" I wonder if it's just a coincidence, or whether the mega-bucketloads of money…
Not to imply that this technology is anything short of fantastic, if you look closely at the video again you will notice fairly obvious artifacts when an object is 'moved' from it's original location - the background replacement is only so good from a single image. Likewise, the 3D objects themselves created by this system show unrealistic artifacts. I'd like to see the results after they expand this system for multi-photo input, of the type used in film with multiple images from a moving camera. My point being, this is a fantastic combination of known technologies to create something truly new, and with refinement will be suitable for feature film work. However, as it is shown in the video, not high enough quality for VFX applications. (Disclaimer: VFX pipeline developer here.)
Question for the entrepreneurs: how would one monetize such a cool algorithm? I come across plenty of cool stuff like this, but without any idea how they can solve real problems.
This tech, as is, is suitable for one to make models of most of their household furniture as well as the rooms of their house. Possible applications: 1) Virtual home makeover, 2) child's "play/doll house" is their own home (virtual or 3D printed)... and on and on and on... Note that this system does not handle irregular, organic shapes (people, plants), so those need a different solution.
The other side of the argument is that social networks improve far more lives than academic research projects like this.
Citation needed.
Is it not self-evident? How many people connect through social networks, which is an obvious benefit? How many people benefit from research papers about 3d model generation from photographs?