Luggage visualization and virtual unpacking

We present a system for luggage visualization where any object is clearly distinguishable from its neighbors. It supports virtual unpacking by visually moving any object away from its original pose. To achieve these, we first apply a volume segmentation guided by a confidence measure that recursively splits connected regions until semantically meaningful objects are obtained, and a label volume whose voxels specifying the object IDs is generated. The original luggage dataset and the label volume are visualized by volume rendering. Through an automatic coloring algorithm, any pair of objects whose projections are adjacent in an image are assigned distinct hues that are modulated onto a transfer function to both reduce rendering cost as well as to improve the smoothness across object boundaries. We have designed a layered framework to efficiently render a scene mixed with packed luggage, animated unpacking objects, and already unpacked objects put aside for further inspection. The system uses GPU to quickly select unpackable objects that are not blocked by others to make the unpacking plausible.