ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans

TL;DR

ScanComplete is a data-driven 3D scene completion and semantic segmentation method that efficiently handles large scenes by using a size-invariant convolutional neural network, achieving superior results in quality and scale.

Contribution

The paper introduces a fully-convolutional generative 3D CNN that manages large scene sizes and a coarse-to-fine inference strategy for high-resolution outputs, advancing 3D scene understanding.

Findings

Outperforms existing methods in large-scale scene completion

Achieves higher semantic segmentation accuracy

Demonstrates efficient processing of large 3D environments

Abstract

We introduce ScanComplete, a novel data-driven approach for taking an incomplete 3D scan of a scene as input and predicting a complete 3D model along with per-voxel semantic labels. The key contribution of our method is its ability to handle large scenes with varying spatial extent, managing the cubic growth in data size as scene size increases. To this end, we devise a fully-convolutional generative 3D CNN model whose filter kernels are invariant to the overall scene size. The model can be trained on scene subvolumes but deployed on arbitrarily large scenes at test time. In addition, we propose a coarse-to-fine inference strategy in order to produce high-resolution output while also leveraging large input context sizes. In an extensive series of experiments, we carefully evaluate different model design choices, considering both deterministic and probabilistic models for completion and semantic inference. Our results show that we outperform other methods not only in the size of the environments handled and processing efficiency, but also with regard to completion quality and semantic segmentation performance by a significant margin.