Comments on "Plane-Based Optimization for 3D Object Reconstruction from Single Line Drawings

I comment on a paper describing a method for inflating a 2D wireframe topological representation of an object to 3D. There are several problems with this paper and the method it describes. An oversimplified problem statement and concentration on mathematical ingenuity rather than comprehension lead the authors to develop a method which is not well-suited to the problem. Failure to take proper account of previous work leads them to compare their method, not with the true state of the art, but with older, less successful approaches. Finally, they omit entirely any mention of, let alone a proposed solution to, the most intractable problem in the area, that of finding resolution sequences.