SG-VAE: Scene Grammar Variational Autoencoder to generate new indoor scenes

TL;DR

This paper introduces SG-VAE, a scene grammar variational autoencoder that automatically learns to generate valid, coherent indoor scene layouts by encoding and decoding scene parse trees, useful for various vision tasks.

Contribution

It presents an automatic grammar extraction method and a grammar-based auto-encoder for generating realistic indoor scenes with valid object arrangements.

Findings

The model generates valid and coherent indoor scene layouts.

It learns meaningful latent representations for scene synthesis.

Applicable to 3D pose and layout estimation tasks.

Abstract

Deep generative models have been used in recent years to learn coherent latent representations in order to synthesize high-quality images. In this work, we propose a neural network to learn a generative model for sampling consistent indoor scene layouts. Our method learns the co-occurrences, and appearance parameters such as shape and pose, for different objects categories through a grammar-based auto-encoder, resulting in a compact and accurate representation for scene layouts. In contrast to existing grammar-based methods with a user-specified grammar, we construct the grammar automatically by extracting a set of production rules on reasoning about object co-occurrences in training data. The extracted grammar is able to represent a scene by an augmented parse tree. The proposed auto-encoder encodes these parse trees to a latent code, and decodes the latent code to a parse tree, thereby ensuring the generated scene is always valid. We experimentally demonstrate that the proposed auto-encoder learns not only to generate valid scenes (i.e. the arrangements and appearances of objects), but it also learns coherent latent representations where nearby latent samples decode to similar scene outputs. The obtained generative model is applicable to several computer vision tasks such as 3D pose and layout estimation from RGB-D data.