GraphGSOcc: Semantic-Geometric Graph Transformer with Dynamic-Static Decoupling for 3D Gaussian Splatting-based Occupancy Prediction
Addressing the task of 3D semantic occupancy prediction for autonomous driving, we tackle two key issues in existing 3D Gaussian Splatting (3DGS) methods: (1) unified feature aggregation neglecting semantic correlations among similar categories and across regions, (2) boundary ambiguities caused by the lack of geometric constraints in MLP iterative optimization and (3) biased issues in dynamic-static object coupling optimization. We propose the GraphGSOcc model, a novel framework that combines semantic and geometric graph Transformer and decouples dynamic-static objects optimization for 3D Gaussian Splatting-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 coarsegrained attention at higher layers models object-level topology. On the other hand, we decouple dynamic and static objects by leveraging semantic probability distributions and design a Dynamic-Static Decoupled Gaussian Attention mechanism to optimize the prediction performance for both dynamic objects and static scenes. GraphGSOcc achieves state-ofthe-art performance on the SurroundOcc-nuScenes, Occ3D-nuScenes, OpenOcc and KITTI occupancy benchmarks. Experiments on the SurroundOcc dataset achieve an mIoU of 25.20%, reducing GPU memory to 6.8 GB, demonstrating a 1.97% mIoU improvement and 13.7% memory reduction compared to GaussianWorld.
Code (0)
등록된 구현이 없습니다.
Tasks
3DGS3D Semantic Occupancy PredictionAutonomous DrivingGPUGraph AttentionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
GraphFusion3D: Dynamic Graph Attention Convolution with Adaptive Cross-Modal Transformer for 3D Object Detection
Despite significant progress in 3D object detection, point clouds remain challenging due to sparse data, incomplete structures, and limited semantic information. Capturing contextual relationships between distant objects…
3D Object DetectionPoint CloudsGTNet: Graph Transformer Network for 3D Point Cloud Classification and Semantic Segmentation
Recently, graph-based and Transformer-based deep learning networks have demonstrated excellent performances on various point cloud tasks. Most of the existing graph methods are based on static graph, which take a fixed i…
3D Point Cloud ClassificationPoint Cloud ClassificationSemantic SegmentationSemantic-Geometric Task Representations for Bimanual Manipulation from Human Demonstrations to Robot Action Planning
Learning structured task representations from human demonstrations is essential for bimanual manipulation, where action ordering, object involvement, and interaction geometry vary significantly across executions. A key c…
The Geometry of Semantic Space: A Continuous Geometric Framework for the Transformer Architecture
We present a continuous geometric framework that models the discrete algebraic operations of the Transformer architecture as an integro-differential equation (IDE) on a semantic fiber bundle calE = calM times R^d. Beginn…
MP-GFormer: A 3D-Geometry-Aware Dynamic Graph Transformer Approach for Machining Process Planning
Machining process planning (MP) is inherently complex due to structural and geometrical dependencies among part features and machining operations. A key challenge lies in capturing dynamic interdependencies that evolve w…
Graph Learning