Two Stream 3D Semantic Scene Completion
share
We propose a new paradigm for advancing 3D semantic scene completion based on RGBD images. We introduce a two stream approach that uses RGB and depth as input channels to a 3D convolutional neural network. Our approach boosts the performance of semantic scene completion by a significant margin. We further provide a study on several input encoding schemes and set a new state of art in 3D semantic scene completion on the NYU dataset.
READ FULL TEXT