Refurnish in 3D: Constructive Tech Demo
17 12 2008by Joshua Koopferstock
Constructive 3D Furniture Demo from joshk on Vimeo.
Usability and time-to-learn are two big concerns with any web application. For 3D applications, both of these factors have led to the downfall of some pretty innovative sites.
In the video above, I demonstrate how we use the Constructive technology to refurnish our own conference room in 3D without having to learn any new or foreign process. With a few points tagged in two pictures by an operator, Constructive understands the camera position, orientation, and focal length, allowing me to move around the 3D furniture along the floor with the correct perspective. And since Constructive understands the relationship between the photos, moving a piece of furniture (or a French maid, as the case may be) in one photo will also move it with the correct perspective in any and all others.
This application also addresses the issue of scalability; by not requiring any highly trained or skilled work to be done, the simple manual tagging process can be cheaply outsourced or put “in the cloud” using Amazon’s Mechanical Turk.
I look forward to seeing innovative retailers using Computer Vision technology like Constructive to add a level personalization that doesn’t exist today. Soon, we won’t have to try to imagine what our new room will look like; you will be able to perfect it before ever putting any money down, and even share your ideas with friends and family to get their thoughts too. A mother knows best, right?
All 3D models used come from www.Presto3D.com
What a brilliant idea of combining the virtual shopping inspiration and 3D computer vision technology!
I wrote an article on this topic further discussing your post.
Augmented Reality for Home Furniture Placement. Welcome your comment too.
Nice,
This is not really new as there are already many companies like metaio.com working on this king of augmented reality apps.
Now room calibration is a thing but there are many other issues that need to be addressed like the creation of the 3D scaled/textured models database (huge work on the furniture vendor side) and as importantly being able to create realistic renderings (meaning taking into account the room lighting conditions / companies like squareclock.com are working on this aspect even if their solution is not AR based).
As an xtra feedback for you guys, I worked on a similar project about two years ago (camera calibration was done from one image).
We started to demonstrate our prototype to potential furniture buyers and what returned was quite surprising. Because of the lack of realism in the scene rendering ( as mentioned above ) our tool did not have the impact we were expecting.
Most of these people mentioned that although it was a “cool app”:
- camera calibration process should be automatic ( marker based is the best solution for now [ see mateio ] - marker less is a must but this is hard )
- the room has to obviously be empty or almost !
- if the rendered furniture is not visually close from reality this is pretty useless unless you consider this tool as a room planner and not a product showcase app
- people want customization features ( color / textures / size variations ….) when possible
So this is maybe a reason why many people prefer to use room planning tools like floorplanner.com (pretty successful) and guys from companies like squareclock focus on rendering quality.
My 2 cents.
It’s nice to see these ideas coming into reality now. This application reminds me of a class project I did ten years ago for an HCI class during my M.Sc. at Georgia Tech. There we explored a similar idea for a virtual interior design assistant, although mainly from an mobile AR interface perspective and just with a crude mockup prototype. In case anybody’s interested, the project web page is still up:
http://www.cc.gatech.edu/computing/classes/cs6751_98_fall/projects/VIDA/