StructureNet: Hierarchical Graph Networks for 3D Shape Generation Figure 1. StructureNet is a hierarchical graph network that produces a unified latent space to encode structured models with both ...

This repository contains a pytorch implementation for the paper GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs. Our work present the first framework capable of generating ...

Accurate and efficient lane detection in 3D space is essential for autonomous driving systems, where robust generalization is the foremost requirement for 3D lane detection algorithms. Considering the ...

Controllability plays a crucial role in the practical applications of 3D indoor scene synthesis. Existing works either allow rough language-based control, that is convenient but lacks fine-grained ...