CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generation
This work addresses the lack of public datasets and methods for 3D semantic urban scene generation, which is important for applications like urban simulation and autonomous driving.
The authors tackled the problem of generating realistic 3D outdoor semantic scenes by introducing SketchSem3D, the first large-scale benchmark for this task, and proposing CymbaDiff, a method that enhances spatial coherence. CymbaDiff achieved superior semantic consistency, spatial realism, and cross-dataset generalization in experiments on SketchSem3D.
Outdoor 3D semantic scene generation produces realistic and semantically rich environments for applications such as urban simulation and autonomous driving. However, advances in this direction are constrained by the absence of publicly available, well-annotated datasets. We introduce SketchSem3D, the first large-scale benchmark for generating 3D outdoor semantic scenes from abstract freehand sketches and pseudo-labeled annotations of satellite images. SketchSem3D includes two subsets, Sketch-based SemanticKITTI and Sketch-based KITTI-360 (containing LiDAR voxels along with their corresponding sketches and annotated satellite images), to enable standardized, rigorous, and diverse evaluations. We also propose Cylinder Mamba Diffusion (CymbaDiff) that significantly enhances spatial coherence in outdoor 3D scene generation. CymbaDiff imposes structured spatial ordering, explicitly captures cylindrical continuity and vertical hierarchy, and preserves both physical neighborhood relationships and global context within the generated scenes. Extensive experiments on SketchSem3D demonstrate that CymbaDiff achieves superior semantic consistency, spatial realism, and cross-dataset generalization. The code and dataset will be available at https://github.com/Lillian-research-hub/CymbaDiff