Abstract

Depthmap fusion is the problem of computing dense 3D re- constructions from a set of depthmaps. Whereas this problem has re- ceived a lot of attention for purely rigid scenes, there is remarkably little prior work for dense reconstructions of scenes consisting of several mov- ing rigid bodies or parts. This paper therefore explores this multi-body depthmap fusion problem. A first observation in the multi-body setting is that when treated naively, ghosting artifacts will emerge, ie. the same part will be reconstructed multiple times at different positions. We there- fore introduce non-intersection constraints which resolve these issues: at any point in time, a point in space can only be occupied by at most one part. Interestingly enough, these constraints can be expressed as linear inequalities and as such define a convex set. We therefore propose to phrase the multi-body depthmap fusion problem in a convex voxel label- ing framework. Experimental evaluation shows that our approach suc- ceeds in computing artifact-free dense reconstructions of the individual parts with a minimal overhead due to the non-intersection constraints.