Contextual Scene Augmentation and Synthesis via GSACNet

TL;DR

GSACNet is a novel system for indoor scene augmentation that effectively trains with limited data using a combination of data augmentation, graph attention, Siamese networks, and autoencoders, outperforming existing methods.

Contribution

Introduces GSACNet, a new scene augmentation framework that operates efficiently with small datasets through a unique combination of neural network architectures and data augmentation techniques.

Findings

GSACNet outperforms prior methods in scene synthesis with limited data.

The proposed system is effective on the Matterport3D dataset.

Ablation studies validate the contribution of each component.

Abstract

Indoor scene augmentation has become an emerging topic in the field of computer vision and graphics with applications in augmented and virtual reality. However, current state-of-the-art systems using deep neural networks require large datasets for training. In this paper we introduce GSACNet, a contextual scene augmentation system that can be trained with limited scene priors. GSACNet utilizes a novel parametric data augmentation method combined with a Graph Attention and Siamese network architecture followed by an Autoencoder network to facilitate training with small datasets. We show the effectiveness of our proposed system by conducting ablation and comparative studies with alternative systems on the Matterport3D dataset. Our results indicate that our scene augmentation outperforms prior art in scene synthesis with limited scene priors available.