Imagen de Portada

RAG-3DSG: Enhancing 3D Scene Graphs with Re-Shot Guided Retrieval-Augmented Generation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chang, Yue, Chen, Rufeng, Zhang, Zhaofan, Chen, Yi, Tian, Yifan, Xie, Sihong
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence Robotics
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

PSG-Nav: Probabilistic Scene Graph Navigation via Multiverse Decision Making
por: Chen, Rufeng, et al.
Publicado: (2026)

MA3DSG: Multi-Agent 3D Scene Graph Generation for Large-Scale Indoor Environments
por: Kim, Yirum, et al.
Publicado: (2026)

Pandora: Articulated 3D Scene Graphs from Egocentric Vision
por: Yu, Alan, et al.
Publicado: (2026)

LOST-3DSG: Lightweight Open-Vocabulary 3D Scene Graphs with Semantic Tracking in Dynamic Environments
por: Ferraina, Sara Micol, et al.
Publicado: (2026)

SceneGraphGrounder: Zero-Shot 3D Visual Grounding via Structured Scene Graph Matching
por: Sun, Xuefei, et al.
Publicado: (2026)

Zero-Shot Robotic Manipulation via 3D Gaussian Splatting-Enhanced Multimodal Retrieval-Augmented Generation
por: Xie, Zilong, et al.
Publicado: (2026)

Perturbation-mitigated USV Navigation with Distributionally Robust Reinforcement Learning
por: Zhang, Zhaofan, et al.
Publicado: (2025)

MSGNav: Unleashing the Power of Multi-modal 3D Scene Graph for Zero-Shot Embodied Navigation
por: Huang, Xun, et al.
Publicado: (2025)

OpenSGA: Efficient 3D Scene Graph Alignment in the Open World
por: Chen, Gang, et al.
Publicado: (2026)

SceneFoundry: Generating Interactive Infinite 3D Worlds
por: Chen, ChunTeng, et al.
Publicado: (2026)

What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Models
por: Deng, Tianchen, et al.
Publicado: (2025)

OpenGraph: Open-Vocabulary Hierarchical 3D Graph Representation in Large-Scale Outdoor Environments
por: Deng, Yinan, et al.
Publicado: (2024)

Neural Attention Field: Emerging Point Relevance in 3D Scenes for One-Shot Dexterous Grasping
por: Wang, Qianxu, et al.
Publicado: (2024)

LEXI-SG: Monocular 3D Scene Graph Mapping with Room-Guided Feed-Forward Reconstruction
por: Kassab, Christina, et al.
Publicado: (2026)

EmbodiedRAG: Dynamic 3D Scene Graph Retrieval for Efficient and Scalable Robot Task Planning
por: Booker, Meghan, et al.
Publicado: (2024)

Graph-Guided Dual-Level Augmentation for 3D Scene Segmentation
por: Lin, Hongbin, et al.
Publicado: (2025)

SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Tasks
por: Xie, Yaxu, et al.
Publicado: (2024)

REACT3D: Recovering Articulations for Interactive Physical 3D Scenes
por: Huang, Zhao, et al.
Publicado: (2025)

Point2Graph: An End-to-end Point Cloud-based 3D Open-Vocabulary Scene Graph for Robot Navigation
por: Xu, Yifan, et al.
Publicado: (2024)

Decoupled Guidance Diffusion for Adaptive Offline Safe Reinforcement Learning
por: Chen, Rufeng, et al.
Publicado: (2026)

3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning
por: Yang, Yuncong, et al.
Publicado: (2024)

SAGE: Scalable Agentic 3D Scene Generation for Embodied AI
por: Xia, Hongchi, et al.
Publicado: (2026)

MobileRAG: Enhancing Mobile Agent with Retrieval-Augmented Generation
por: Loo, Gowen, et al.
Publicado: (2025)

FunGraph: Functionality Aware 3D Scene Graphs for Language-Prompted Scene Interaction
por: Rotondi, Dennis, et al.
Publicado: (2025)

KeySG: Hierarchical Keyframe-Based 3D Scene Graphs
por: Werby, Abdelrhman, et al.
Publicado: (2025)

PlaceIt3D: Language-Guided Object Placement in Real 3D Scenes
por: Abdelreheem, Ahmed, et al.
Publicado: (2025)

DGSG-Mind: Dynamic 3D Gaussian Scene Graphs for Long-Term Scene Understanding and Grounding
por: Ge, Luzhou, et al.
Publicado: (2026)

INHerit-SG: Incremental Hierarchical Semantic Scene Graphs with RAG-Style Retrieval
por: Fang, YukTungSamuel, et al.
Publicado: (2026)

SHOW3D: Capturing Scenes of 3D Hands and Objects in the Wild
por: Rim, Patrick, et al.
Publicado: (2026)

SignRAG: A Retrieval-Augmented System for Scalable Zero-Shot Road Sign Recognition
por: Zhu, Minghao, et al.
Publicado: (2025)

Articulate3D: Holistic Understanding of 3D Scenes as Universal Scene Description
por: Halacheva, Anna-Maria, et al.
Publicado: (2024)

Text-Scene: A Scene-to-Language Parsing Framework for 3D Scene Understanding
por: Li, Haoyuan, et al.
Publicado: (2025)

ZING-3D: Zero-shot Incremental 3D Scene Graphs via Vision-Language Models
por: Saxena, Pranav, et al.
Publicado: (2025)

RGB-only Active 3D Scene Graph Generation for Indoor Mobile Robots
por: Modi, Giorgia, et al.
Publicado: (2026)

Rheos: Modelling Continuous Motion Dynamics in Hierarchical 3D Scene Graphs
por: Catalano, Iacopo, et al.
Publicado: (2026)

SGAligner++: Cross-Modal Language-Aided 3D Scene Graph Alignment
por: Singh, Binod, et al.
Publicado: (2025)

Online 3D Scene Reconstruction Using Neural Object Priors
por: Chabal, Thomas, et al.
Publicado: (2025)

GSMem: 3D Gaussian Splatting as Persistent Spatial Memory for Zero-Shot Embodied Exploration and Reasoning
por: Lu, Yiren, et al.
Publicado: (2026)

SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes
por: Huang, Jiaxin, et al.
Publicado: (2025)

Quantile Geometry Regularization for Distributional Reinforcement Learning
por: Zhang, Zhaofan, et al.
Publicado: (2026)