Halluci-Net: Scene Completion by Exploiting Object Co-occurrence Relationships

We address the new problem of complex scene completion from sparse label maps. We use a two-stage deep network based method, called `Halluci-Net', that uses object co-occurrence relationships to produce a dense and complete label map. The generated dense label map is fed into a state-of-the-art image synthesis method to obtain the final image. The proposed method is evaluated on the Cityscapes dataset and it outperforms a single-stage baseline method on various performance metrics like Fr\'echet Inception Distance (FID), semantic segmentation accuracy, and similarity in object co-occurrences. In addition to this, we show qualitative results on a subset of ADE20K dataset containing bedroom images.