Graph Transformer GANs for Graph-Constrained House Generation

by   Hao Tang, et al.

We present a novel graph Transformer generative adversarial network (GTGAN) to learn effective graph node relations in an end-to-end fashion for the challenging graph-constrained house generation task. The proposed graph-Transformer-based generator includes a novel graph Transformer encoder that combines graph convolutions and self-attentions in a Transformer to model both local and global interactions across connected and non-connected graph nodes. Specifically, the proposed connected node attention (CNA) and non-connected node attention (NNA) aim to capture the global relations across connected nodes and non-connected nodes in the input graph, respectively. The proposed graph modeling block (GMB) aims to exploit local vertex interactions based on a house layout topology. Moreover, we propose a new node classification-based discriminator to preserve the high-level semantic and discriminative node features for different house components. Finally, we propose a novel graph-based cycle-consistency loss that aims at maintaining the relative spatial relationships between ground truth and predicted graphs. Experiments on two challenging graph-constrained house generation tasks (i.e., house layout and roof generation) with two public datasets demonstrate the effectiveness of GTGAN in terms of objective quantitative scores and subjective visual realism. New state-of-the-art results are established by large margins on both tasks.


page 2

page 6

page 7


Bipartite Graph Reasoning GANs for Person Pose and Facial Image Synthesis

We present a novel bipartite graph reasoning Generative Adversarial Netw...

Learning to Identify Graphs from Node Trajectories in Multi-Robot Networks

The graph identification problem consists of discovering the interaction...

Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs

Recent graph-to-text models generate text from graph-based data using ei...

An Unpooling Layer for Graph Generation

We propose a novel and trainable graph unpooling layer for effective gra...

Layout-Graph Reasoning for Fashion Landmark Detection

Detecting dense landmarks for diverse clothes, as a fundamental techniqu...

Revisiting Transformer for Point Cloud-based 3D Scene Graph Generation

In this paper, we propose the semantic graph Transformer (SGT) for the 3...

Tackling the Challenges in Scene Graph Generation with Local-to-Global Interactions

In this work, we seek new insights into the underlying challenges of the...

Please sign up or login with your details

Forgot password? Click here to reset