GraphGSOcc: Semantic and Geometric Graph Transformer for 3D Gaussian Splating-based Occupancy Prediction

Addressing the task of 3D semantic occupancy prediction for autonomous driving, we tackle two key issues in existing 3D Gaussian Splating (3DGS) methods: (1) unified feature aggregation neglecting semantic correlations among similar categories and across regions, and (2) boundary ambiguities caused by the lack of geometric constraints in MLP iterative optimization. We propose the GraphGSOcc model, a novel framework that combines semantic and geometric graph Transformer for 3D Gaussian Splating-based Occupancy Prediction. We propose the Dual Gaussians Graph Attenntion, which dynamically constructs dual graph structures: a geometric graph adaptively calculating KNN search radii based on Gaussian poses, enabling large-scale Gaussians to aggregate features from broader neighborhoods while compact Gaussians focus on local geometric consistency; a semantic graph retaining top-M highly correlated nodes via cosine similarity to explicitly encode semantic relationships within and across instances. Coupled with the Multi-scale Graph Attention framework, fine-grained attention at lower layers optimizes boundary details, while coarse-grained attention at higher layers models object-level topology. Experiments on the SurroundOcc dataset achieve an mIoU of 24.10%, reducing GPU memory to 6.1 GB, demonstrating a 1.97% mIoU improvement and 13.7% memory reduction compared to GaussianWorld

@article{song2025_2506.14825,
  title={ GraphGSOcc: Semantic-Geometric Graph Transformer with Dynamic-Static Decoupling for 3D Gaussian Splatting-based Occupancy Prediction },
  author={ Ke Song and Yunhe Wu and Chunchit Siu and Huiyuan Xiong },
  journal={arXiv preprint arXiv:2506.14825},
  year={ 2025 }
}