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

• URL: http://arxiv.org/abs/2512.02991v1
• Date: Tue, 02 Dec 2025 18:05:02 GMT
• Title: GraphFusion3D: Dynamic Graph Attention Convolution with Adaptive Cross-Modal Transformer for 3D Object Detection
• Authors: Md Sohag Mia, Md Nahid Hasan, Tawhid Ahmed, Muhammad Abdullah Adnan,
• Abstract summary: We propose GraphFusion3D, a unified framework combining multi-modal fusion with advanced feature learning.<n>Our approach introduces the Adaptive Cross-Modal Transformer (ACMT), which adaptively integrates image features into point representations to enrich both geometric and semantic information.<n>For proposal refinement, we introduce the Graph Reasoning Module (GRM), a novel mechanism that models neighborhood relationships to simultaneously capture local geometric structures and global semantic context.
• Score: 1.1106255381859969
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 presents additional difficulties. To address these challenges, we propose GraphFusion3D, a unified framework combining multi-modal fusion with advanced feature learning. Our approach introduces the Adaptive Cross-Modal Transformer (ACMT), which adaptively integrates image features into point representations to enrich both geometric and semantic information. For proposal refinement, we introduce the Graph Reasoning Module (GRM), a novel mechanism that models neighborhood relationships to simultaneously capture local geometric structures and global semantic context. The module employs multi-scale graph attention to dynamically weight both spatial proximity and feature similarity between proposals. We further employ a cascade decoder that progressively refines detections through multi-stage predictions. Extensive experiments on SUN RGB-D (70.6\% AP$_{25}$ and 51.2\% AP$_{50}$) and ScanNetV2 (75.1\% AP$_{25}$ and 60.8\% AP$_{50}$) demonstrate a substantial performance improvement over existing approaches.

Related papers

• MGCA-Net: Multi-Graph Contextual Attention Network for Two-View Correspondence Learning [18.21720738180151]
  Two-view correspondence learning is a key task in computer vision.<n>We propose a Multi-Graph Contextual Attention Network (MGCA-Net)<n>We show that MGCA-Net significantly outperforms existing SOTA methods in the outlier rejection and camera pose estimation tasks.
  arXiv  Detail & Related papers  (2025-12-29T10:58:40Z)
• Object-Centric Representation Learning for Enhanced 3D Scene Graph Prediction [3.7471945679132594]
  3D Semantic Scene Graph Prediction aims to detect objects and their semantic relationships in 3D scenes.<n>Previous research has addressed dataset limitations and explored various approaches including Open-Vocabulary settings.<n>We demonstrate through extensive analysis that the quality of object features plays a critical role in determining overall scene graph accuracy.
  arXiv  Detail & Related papers  (2025-10-06T11:33:09Z)
• TriCLIP-3D: A Unified Parameter-Efficient Framework for Tri-Modal 3D Visual Grounding based on CLIP [52.79100775328595]
  3D visual grounding allows an embodied agent to understand visual information in real-world 3D environments based on human instructions.<n>Existing 3D visual grounding methods rely on separate encoders for different modalities.<n>We propose a unified 2D pre-trained multi-modal network to process all three modalities.
  arXiv  Detail & Related papers  (2025-07-20T10:28:06Z)
• Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformers [59.0181939916084]
  Traditional 3D networks mainly focus on local geometric details and ignore the topological structure between local geometries. We propose a novel Priors Distillation (RPD) method to extract priors from the well-trained transformers on massive images. Experiments on the PointDA-10 and the Sim-to-Real datasets verify that the proposed method consistently achieves the state-of-the-art performance of UDA for point cloud classification.
  arXiv  Detail & Related papers  (2024-07-26T06:29:09Z)
• DAMSDet: Dynamic Adaptive Multispectral Detection Transformer with Competitive Query Selection and Adaptive Feature Fusion [82.2425759608975]
  Infrared-visible object detection aims to achieve robust even full-day object detection by fusing the complementary information of infrared and visible images. We propose a Dynamic Adaptive Multispectral Detection Transformer (DAMSDet) to address these two challenges. Experiments on four public datasets demonstrate significant improvements compared to other state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-03-01T07:03:27Z)
• S^2Former-OR: Single-Stage Bi-Modal Transformer for Scene Graph Generation in OR [50.435592120607815]
  Scene graph generation (SGG) of surgical procedures is crucial in enhancing holistically cognitive intelligence in the operating room (OR) Previous works have primarily relied on multi-stage learning, where the generated semantic scene graphs depend on intermediate processes with pose estimation and object detection. In this study, we introduce a novel single-stage bi-modal transformer framework for SGG in the OR, termed S2Former-OR.
  arXiv  Detail & Related papers  (2024-02-22T11:40:49Z)
• Spatial-Temporal Graph Enhanced DETR Towards Multi-Frame 3D Object Detection [54.041049052843604]
  We present STEMD, a novel end-to-end framework that enhances the DETR-like paradigm for multi-frame 3D object detection. First, to model the inter-object spatial interaction and complex temporal dependencies, we introduce the spatial-temporal graph attention network. Finally, it poses a challenge for the network to distinguish between the positive query and other highly similar queries that are not the best match.
  arXiv  Detail & Related papers  (2023-07-01T13:53:14Z)
• Similarity-Aware Fusion Network for 3D Semantic Segmentation [87.51314162700315]
  We propose a similarity-aware fusion network (SAFNet) to adaptively fuse 2D images and 3D point clouds for 3D semantic segmentation. We employ a late fusion strategy where we first learn the geometric and contextual similarities between the input and back-projected (from 2D pixels) point clouds. We show that SAFNet significantly outperforms existing state-of-the-art fusion-based approaches across various data integrity.
  arXiv  Detail & Related papers  (2021-07-04T09:28:18Z)
• Relation Transformer Network [25.141472361426818]
  We propose a novel transformer formulation for scene graph generation and relation prediction. We leverage the encoder-decoder architecture of the transformer for rich feature embedding of nodes and edges. Our relation prediction module classifies the directed relation from the learned node and edge embedding.
  arXiv  Detail & Related papers  (2020-04-13T20:47:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.