trf-sg2im

Model card for the paper "Transformer-Based Image Generation from Scene Graphs". Original GitHub implementation here.

Model

This model is a two-stage scene-graph-to-image approach. It takes a scene graph as input and generates a layout using a transformer-based architecture with Laplacian Positional Encoding. Then, it uses this estimated layout to condition an autoregressive GPT-like transformer to compose the image in the latent, discrete space, converted into the final image by a VQVAE.

Usage

For usage instructions, please refer to the original GitHub repo.

Results

Comparison with other state-of-the-art approaches