3D scene generation from scene graphs and self-attention

arXiv:2404.01887v2 Announce Type: replace
Abstract: Synthesizing realistic and diverse indoor 3D scene layouts in a controllable fashion opens up applications in simulated navigation and virtual reality. As concise and robust representations of a scene, scene graphs have proven to be well-suited as the semantic control on the generated layout. We present a variant of the conditional variational autoencoder (cVAE) model to synthesize 3D scenes from scene graphs and floor plans. We exploit the properties of self-attention layers to capture high-level …

3d scene generation abstract applications arxiv attention control cs.cv diverse fashion generated graphs navigation reality robust self-attention semantic type virtual virtual reality