We propose a novel data-driven shape completion algorithm that leverages both a database of example segmented shapes and symmetry priors to estimate the geometry of the occluded regions. The main...

We present a consolidation method that is based on a new representation of 3D point sets. The key idea is to augment each surface point into a deep point by associating it with an inner point that...

We propose autonomous scanning of indoor scenes by a robot. We develop a framework which couples scene reconstruction with proactive object analysis. The output is object-aware scene reconstruction...

Unsynchronized Structured Light is a novel method for high resolution and high accuracy 3D snapshot capture for DSLRs and smartphones, which does not require synchronization of patterns and images....

We generate 3D scenes that allow the same activities as real environments captured through noisy and incomplete 3D scans. Our core contribution is a new scene synthesis technique which, conditioned...