SGR3 Model: Scene Graph Retrieval-Reasoning Model in 3D

• URL: http://arxiv.org/abs/2603.04614v1
• Date: Wed, 04 Mar 2026 21:19:54 GMT
• Title: SGR3 Model: Scene Graph Retrieval-Reasoning Model in 3D
• Authors: Zirui Wang, Ruiping Liu, Yufan Chen, Junwei Zheng, Weijia Fan, Kunyu Peng, Di Wen, Jiale Wei, Jiaming Zhang, Rainer Stiefelhagen,
• Abstract summary: 3D scene graphs provide a structured representation of object entities and their relationships.<n>Existing approaches for 3D scene graph generation typically combine scene reconstruction with graph neural networks (GNNs)<n>In this work, we introduce a Scene Graph Retrieval-Reasoning Model in 3D (SGR3 Model)
• Score: 51.32219731589742
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 3D scene graphs provide a structured representation of object entities and their relationships, enabling high-level interpretation and reasoning for robots while remaining intuitively understandable to humans. Existing approaches for 3D scene graph generation typically combine scene reconstruction with graph neural networks (GNNs). However, such pipelines require multi-modal data that may not always be available, and their reliance on heuristic graph construction can constrain the prediction of relationship triplets. In this work, we introduce a Scene Graph Retrieval-Reasoning Model in 3D (SGR3 Model), a training-free framework that leverages multi-modal large language models (MLLMs) with retrieval-augmented generation (RAG) for semantic scene graph generation. SGR3 Model bypasses the need for explicit 3D reconstruction. Instead, it enhances relational reasoning by incorporating semantically aligned scene graphs retrieved via a ColPali-style cross-modal framework. To improve retrieval robustness, we further introduce a weighted patch-level similarity selection mechanism that mitigates the negative impact of blurry or semantically uninformative regions. Experiments demonstrate that SGR3 Model achieves competitive performance compared to training-free baselines and on par with GNN-based expert models. Moreover, an ablation study on the retrieval module and knowledge base scale reveals that retrieved external information is explicitly integrated into the token generation process, rather than being implicitly internalized through abstraction.

Related papers

• GeoSceneGraph: Geometric Scene Graph Diffusion Model for Text-guided 3D Indoor Scene Synthesis [14.137982018879049]
  Methods that synthesize indoor 3D scenes from text prompts have wide-ranging applications in film production, interior design, video games, virtual reality, and synthetic data generation for training embodied agents.<n>Existing approaches typically either train generative models from scratch or leverage vision-language models (VLMs)<n>We introduce GeoSceneGraph, a method that synthesizes 3D scenes from text prompts by leveraging the graph structure and geometric symmetries of 3D scenes.
  arXiv  Detail & Related papers  (2025-11-18T20:06:49Z)
• Compile Scene Graphs with Reinforcement Learning [69.36723767339001]
  Next-token prediction is the fundamental principle for training large language models (LLMs)<n>We introduce R1-SGG, a multimodal LLM (M-LLM) initially trained via supervised fine-tuning (SFT) on the scene graph dataset.<n>We design a set of graph-centric rewards, including three recall-based variants -- Hard Recall, Hard Recall+Relax, and Soft Recall.
  arXiv  Detail & Related papers  (2025-04-18T10:46:22Z)
• Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding [50.448520056844885]
  We propose a generative Bayesian network to produce diverse synthetic scenes with real-world patterns. A series of experiments robustly display our method's consistent superiority over existing state-of-the-art pre-training approaches.
  arXiv  Detail & Related papers  (2024-06-17T07:43:53Z)
• Incremental 3D Semantic Scene Graph Prediction from RGB Sequences [86.77318031029404]
  We propose a real-time framework that incrementally builds a consistent 3D semantic scene graph of a scene given an RGB image sequence. Our method consists of a novel incremental entity estimation pipeline and a scene graph prediction network. The proposed network estimates 3D semantic scene graphs with iterative message passing using multi-view and geometric features extracted from the scene entities.
  arXiv  Detail & Related papers  (2023-05-04T11:32:16Z)
• VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud [51.063494002003154]
  3D semantic scene graph (3DSSG) prediction in the point cloud is challenging since the 3D point cloud only captures geometric structures with limited semantics compared to 2D images. We propose Visual-Linguistic Semantics Assisted Training scheme that can significantly empower 3DSSG prediction models with discrimination about long-tailed and ambiguous semantic relations.
  arXiv  Detail & Related papers  (2023-03-25T09:14:18Z)
• Explore Contextual Information for 3D Scene Graph Generation [43.66442227874461]
  3D scene graph generation (SGG) has been of high interest in computer vision. We propose a framework fully exploring contextual information for the 3D SGG task. Our approach achieves superior or competitive performance over previous methods on the 3DSSG dataset.
  arXiv  Detail & Related papers  (2022-10-12T14:26:17Z)
• Hierarchical Graph Networks for 3D Human Pose Estimation [50.600944798627786]
  Recent 2D-to-3D human pose estimation works tend to utilize the graph structure formed by the topology of the human skeleton. We argue that this skeletal topology is too sparse to reflect the body structure and suffer from serious 2D-to-3D ambiguity problem. We propose a novel graph convolution network architecture, Hierarchical Graph Networks, to overcome these weaknesses.
  arXiv  Detail & Related papers  (2021-11-23T15:09:03Z)
• A Deep Latent Space Model for Graph Representation Learning [10.914558012458425]
  We propose a Deep Latent Space Model (DLSM) for directed graphs to incorporate the traditional latent variable based generative model into deep learning frameworks. Our proposed model consists of a graph convolutional network (GCN) encoder and a decoder, which are layer-wise connected by a hierarchical variational auto-encoder architecture. Experiments on real-world datasets show that the proposed model achieves the state-of-the-art performances on both link prediction and community detection tasks.
  arXiv  Detail & Related papers  (2021-06-22T12:41:19Z)

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.