Semantic Scene Completion Combining Colour and Depth: preliminary experiments

Abstract

Semantic scene completion is the task of producing a complete 3D voxel representation of volumetric occupancy with semantic labels for a scene from a single-view observation. We built upon the recent work of Song et al. (CVPR 2017), who proposed SSCnet, a method that performs scene completion and semantic labelling in a single end-to-end 3D convolutional network. SSCnet uses only depth maps as input, even though depth maps are usually obtained from devices that also capture colour information, such as RGBD sensors and stereo cameras. In this work, we investigate the potential of the RGB colour channels to improve SSCnet.

arXiv comment5 pages, 2 figures

References in corpus (4)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Multi-Scale Context Aggregation by Dilated Convolutions
• Predicting Complete 3D Models of Indoor Scenes
• Semantic Scene Completion from a Single Depth Image

Cited by in corpus (6)

• EdgeNet: Semantic Scene Completion from a Single RGB-D Image
• RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion
• Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completion
• View-volume Network for Semantic Scene Completion from a Single Depth Image
• Semantic Scene Completion via Integrating Instances and Scene in-the-Loop
• Attention-based Multi-modal Fusion Network for Semantic Scene Completion