There’re about 1,500 synths with the “car” tag already. But Photosynthing cars is one of the more difficult things to do, and car synths often don’t work out as well as room synths, art synths, landscape synths, or even people synths. The lines and the details on the shape of the car that Photosynth would normally use for edge detection are often changed visually because of the gloss of the finish. Next time you’re looking at a shiny car, notice how as you move around it the surface of the car almost morphs through colors and reflections. What often happens when synthing a car is that the background gets matched much more than the car, resulting in a very poor point cloud, and a frustrating navigation experience. “One of the first steps in Photosynth processing pipeline is “feature extraction”. This’s where we analyze each photo and look for areas of interesting texture that we hope can later be matched to textures in other photos. Notice that I said “texture”, because Photosynth doesn’t look for corners or edges; it looks for areas of visual “roughness”. Our feature detection algorithm was inspired by the popular SIFT Algorithm created by David Lowe at UBC.” Read here for some tips on how best to shoot a car for a synth, inside and out.