ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans
This addresses the challenge of handling large-scale 3D scene reconstruction and labeling for applications like robotics and augmented reality, representing a novel method for a known bottleneck.
The authors tackled the problem of completing incomplete 3D scans and performing semantic segmentation for large scenes, achieving significant improvements in completion quality and semantic segmentation performance over other methods.
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.