Towards Part-Based Understanding of RGB-D Scans

Figure 1 : From an input RGB-D scan (left), we propose to detect objects in the scan and predict their complete part decompositions as semantic part completion; that is, we predict the part masks for the complete object, inferring the part geometry of any missing or unobserved regions in the scan. To achieve this, we predict the part structure of each detected object to drive a geometric prior-driven prediction of the complete part masks.