Boosting Self-Supervision for Single-View Scene Completion via Knowledge Distillation

direct supervision b) knowledge distillation a) self-supervised scene reconstruction multi-view scene reconstruction single-view scene reconstruction rendering density color sampled points density field Figure 1. Knowledge Distillation from Multi-View to Single-View. We propose to boost single-view scene completion by exploiting additional information from multiple images. a) we first train a novel multi-view scene reconstruction algorithm that is able to fuse density fields from multiple images in a fully self-supervised manner. b) we then employ knowledge distillation to directly supervise a state-ofthe-art single-view reconstruction model in 3D to boost its performance.