Figure 10. Modeling from sketches. Input sketches are taken from Ref. 19

(a) (b) (c)

Figure 11. Failures. (a) Due to perspective projection, the table legs cannot be snapped to the image under a parallelism constraint. (b) Due to the assumption of uniformly scaling profiles, the bottom of the toothpaste tube is not flattened. (c) Snapping fails due to an ill-defined edge caused by the shadow cast by the bottle.

Figure 1 6 8 7 9

Example Menorah (a) (b) (c) (d/e) (f) Obelisk Tap Lamp Telescope Trumpet Handle Horn Time (s) 80 + 25 75 + 15 20 35 30 65 + 35 20 30 + 25 40 + 50 100 + 30 80 30 60 Constraints 2 4 2 1 1 1 0 2 1 2 1 1 1 Table 1. Modeling + Editing times (in seconds), and the number of manually provided geo-semantic constraints (added or removed) for each example.

7. CONCLUSION

We have presented an interactive technique which can model
3D man-made objects from a single photograph by combin-
ing the cognitive ability of humans with the computational
accuracy of computers. The 3-Sweep technique is designed to
allow extracting an editable model from a single image. The
range of objects that our technique can support are objects
that consist of simple parts, without much occlusion. As we
demonstrated, this range is surprising large to be useful for
interactive modeling—our tests show that our method can
model a large variety of man-made objects in photographs, as
well as objects in sketches. The modeled objects can be edited
in a semantically meaningful way, both in the original image,
or for use in composing new images. In the future, we hope to
extend the range of primitives, and to allow modeling of the
includes typical relationships among parts such as symmetry,
parallelism, and collinearity. More free-form objects, or parts,
that differ from this would need to be positioned by hand.

Even for a generalized cylinder there is sometimes ambiguity. We assume that the profiles of the cylinder are uniformly scaled and do not rotate around the main axis. This assumption is not always satisfied, as demonstrated in Figure 11b. We further assume that the main axis is mostly visible and parallel to the viewing plane. Using a perspective assumption, we can handle a small amount of skew, but not a large one.

The snapping algorithm relies on good detection of object edges and assumes the main part of the object is not occluded. Objects that are too small, such as the cross in Figure 6e, or objects that have fuzzy edges such as the example in Figure 11c are hard to model accurately. The photographs themselves often have some distortions from an ideal perspective projection (see Figure 11a), where corrections should be applied before modeling. Lastly, our editing assumes a simple illumination model without shadows. Relighting and shadow computations are not currently supported by our system.