Semantic Scene Completion from a Single Depth Image

TL;DR

This paper introduces SSCNet, an end-to-end 3D convolutional network that jointly performs semantic scene completion from a single depth image, effectively combining occupancy and semantic labeling tasks.

Contribution

The paper presents SSCNet, a novel deep learning architecture that simultaneously predicts 3D occupancy and semantic labels from a single depth image, leveraging a dilation-based context module.

Findings

Joint model outperforms separate task approaches

Effective use of a large synthetic dataset for training

Improved accuracy in semantic scene completion

Abstract

This paper focuses on semantic scene completion, a task for producing a complete 3D voxel representation of volumetric occupancy and semantic labels for a scene from a single-view depth map observation. Previous work has considered scene completion and semantic labeling of depth maps separately. However, we observe that these two problems are tightly intertwined. To leverage the coupled nature of these two tasks, we introduce the semantic scene completion network (SSCNet), an end-to-end 3D convolutional network that takes a single depth image as input and simultaneously outputs occupancy and semantic labels for all voxels in the camera view frustum. Our network uses a dilation-based 3D context module to efficiently expand the receptive field and enable 3D context learning. To train our network, we construct SUNCG - a manually created large-scale dataset of synthetic 3D scenes with dense volumetric annotations. Our experiments demonstrate that the joint model outperforms methods addressing each task in isolation and outperforms alternative approaches on the semantic scene completion task.