Comment by rywang
15 years ago
The buildings are meticulously 3-D modeled and texture mapped--you can see the texture repetition artifacts. I've read some research about automatic modeling techniques from street view images+, but I'd suspect this was done by hand.
+ http://web.mit.edu/jxiao/Public/publication/2009/TOG/paper_h...
Looks like China's cheap labor is bridging the gap to AI.
This is essentially the same as a traditional animated movie: gigantic sum of work to do, essentially infinitely parallel, and capable of being process-optimized such that two adjacent frames require much less work than freehanding them. They're probably using a large library of templated buildings (how many silhouettes are there at that resolution, really?), brushes, and then just applying detail work to the significant ones.
It's a big job, and it's impressive, but it isn't "We had enough people to freehand a scale map of the entire country, bwahaha."
Perhaps they'll perform Searle's "Chinese room" experiment IRL.
Props for the reference, but aside from matching /Chin/ the Chinese room has absolutely nothing to do with this approach. It is staffed by a single guy and it is critically important to the thought experiment that he does not understand Chinese.
(Brief sketch of the Chinese room: there is a locked room with a slit which permits paper to come in and paper to go out. Inside the room is a man who does not speak Chinese. He receives paper with Chinese symbols on it, consults a vast library of books with rules on what to do in response to particular symbols, laboriously copies his response onto paper, and pushes it out through the slit. The response is intelligible as Chinese responsive to the input Chinese. Searle argues that the man can't understand Chinese. Personal opinion: it's navelgazing that only matters to philosophy, but I think the man and books together constitute a system which speaks Chinese, in the same way that people bidding in an auction together constitute an efficient price discovery mechanism even if none has expert knowledge of the "true value" of all items at auction.)
4 replies →
The real question is, is this more useful than the photographic approach? i.e. does a user identify these landmarks better in this slightly abstracted hand drawn rendering than in a photo rendering of the same?
There's less cognitive overhead in processing these renderings because there's less stuff to pay attention to. A photograph tends to record everything, which can be overwhelming if you're looking for select landmarks.
Also, the real world tends to be more drab and polluted than these cheery 100% saturation renderings.
Is it fully 3D rendered? or just an isometric view like the old simcity? You can't rotate the viewpoint, as far as I've seen (but as I don't know Chinese I might be wrong).
Seriously by hand? How many mechanical turks? Why do you say so? The textures and all seem to suggest otherwise. I am very much interested in the actual technology. Perhaps the textures were superimposed on the 3d models and not a direct input of the 3d modelling.
The cost of labor in China is still low enough for this to happen.
The research done by your fellow in MIT while in HKUST is also very impressive. Just that the result is not the same kind found in here - the one here is simply artistic model, not a realistic one.