Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis

Understand

We introduce a data-driven approach to complete partial 3D shapes through a combination of volumetric deep neural networks and 3D shape synthesis.

• From a partially-scanned input shape, our method first infers a low-resolution -- but complete -- output.
• To this end, we introduce a 3D-Encoder-Predictor Network (3D-EPN) which is composed of 3D convolutional layers.
• The network is trained to predict and fill in missing data, and operates on an implicit surface representation that encodes both known and unknown space.