paper-with-me

Papers

GraphGSOcc: Semantic-Geometric Graph Transformer with Dynamic-Static Decoupling for 3D Gaussian Splatting-based Occupancy Prediction

2025-06-13 · Ke Song, Yunhe Wu, Chunchit Siu, Huiyuan Xiong

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.

📄 PDF Abstract BibTeX arXiv:2506.14825

Code (0)

등록된 구현이 없습니다.

Tasks

3DGS3D Semantic Occupancy PredictionAutonomous DrivingGPUGraph Attention

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Transformer A Transformer is a model architecture that eschews recurrence and instead relies entirely on an [attention…

Similar Papers 제목 키워드 기반

GraphFusion3D: Dynamic Graph Attention Convolution with Adaptive Cross-Modal Transformer for 3D Object Detection

2025-12-02 · Md Sohag Mia, Md Nahid Hasan, Muhammad Abdullah Adnan arxiv

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 Clouds

GTNet: Graph Transformer Network for 3D Point Cloud Classification and Semantic Segmentation

2023-05-24 · Wei Zhou, Qian Wang, Weiwei Jin, Xinzhe Shi 외

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 Segmentation

Semantic-Geometric Task Representations for Bimanual Manipulation from Human Demonstrations to Robot Action Planning

2026-01-16 · Franziska Herbert, Vignesh Prasad, Han Liu, Dorothea Koert 외 arxiv

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

2026-07-19 · Zhihua Liang hf

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

2025-11-14 · Fatemeh Elhambakhsh, Gaurav Ameta, Aditi Roy, Hyunwoong Ko arxiv

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