Deep Learned Full-3D Object Completion from Single View

TL;DR

This paper introduces a deep learning approach for 3D object completion from a single view, using a neural network trained on synthetic data to accurately reconstruct unseen objects in real-time.

Contribution

It presents a compact neural network that learns 3D geometric features offline, enabling efficient and accurate object reconstruction from single depth views.

Findings

Achieves 92.9% reconstruction accuracy at 30x30x30 resolution

Uses roughly 1/4 the weights of leading networks

Enables real-time 3D reconstruction applications

Abstract

3D geometry is a very informative cue when interacting with and navigating an environment. This writing proposes a new approach to 3D reconstruction and scene understanding, which implicitly learns 3D geometry from depth maps pairing a deep convolutional neural network architecture with an auto-encoder. A data set of synthetic depth views and voxelized 3D representations is built based on ModelNet, a large-scale collection of CAD models, to train networks. The proposed method offers a significant advantage over current, explicit reconstruction methods in that it learns key geometric features offline and makes use of those to predict the most probable reconstruction of an unseen object. The relatively small network, consisting of roughly 4 million weights, achieves a 92.9% reconstruction accuracy at a 30x30x30 resolution through the use of a pre-trained decompression layer. This is roughly 1/4 the weights of the current leading network. The fast execution time of the model makes it suitable for real-time applications.