Two Stream 3D Semantic Scene Completion
This work addresses semantic scene completion for robotics or AR/VR applications, representing an incremental advance by combining depth and semantic streams.
The paper tackles the problem of inferring 3D geometry and semantics of occluded surfaces from a single depth image, proposing a two-stream approach that uses depth and RGB-derived semantic information to predict a complete 3D semantic tensor, resulting in substantial performance improvements over state-of-the-art methods.
Inferring the 3D geometry and the semantic meaning of surfaces, which are occluded, is a very challenging task. Recently, a first end-to-end learning approach has been proposed that completes a scene from a single depth image. The approach voxelizes the scene and predicts for each voxel if it is occupied and, if it is occupied, the semantic class label. In this work, we propose a two stream approach that leverages depth information and semantic information, which is inferred from the RGB image, for this task. The approach constructs an incomplete 3D semantic tensor, which uses a compact three-channel encoding for the inferred semantic information, and uses a 3D CNN to infer the complete 3D semantic tensor. In our experimental evaluation, we show that the proposed two stream approach substantially outperforms the state-of-the-art for semantic scene completion.