# 3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding

arXiv: https://arxiv.org/abs/2412.18450 · HTML: https://mlsanity.com/paper/2412.18450/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 66 references that are in the map.
- First posted on arXiv 24 Dec 2024.

## Builds on (most cited first, 30 of 46)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](https://mlsanity.com/paper/1912.08830/) (2019)
- [An Embodied Generalist Agent in 3D World](https://mlsanity.com/paper/2311.12871/) (2023)
- [ScanQA: 3D Question Answering for Spatial Scene Understanding](https://mlsanity.com/paper/2112.10482/) (2021)
- [Image Generation from Scene Graphs](https://mlsanity.com/paper/1804.01622/) (2018)
- [SQA3D: Situated Question Answering in 3D Scenes](https://mlsanity.com/paper/2210.07474/) (2022)
- [Mask3D: Mask Transformer for 3D Semantic Instance Segmentation](https://mlsanity.com/paper/2210.03105/) (2022)
- [Auto-Encoding Scene Graphs for Image Captioning](https://mlsanity.com/paper/1812.02378/) (2018)
- [Uni3D: Exploring Unified 3D Representation at Scale](https://mlsanity.com/paper/2310.06773/) (2023)
- [Scan2Cap: Context-aware Dense Captioning in RGB-D Scans](https://mlsanity.com/paper/2012.02206/) (2020)
- [3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment](https://mlsanity.com/paper/2308.04352/) (2023)
- [Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation](https://mlsanity.com/paper/2403.17846/) (2024)
- [RIO: 3D Object Instance Re-Localization in Changing Indoor Environments](https://mlsanity.com/paper/1908.06109/) (2019)
- [Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers](https://mlsanity.com/paper/2312.08168/) (2023)
- [Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning](https://mlsanity.com/paper/2403.11401/) (2024)
- [Multi3DRefer: Grounding Text Description to Multiple 3D Objects](https://mlsanity.com/paper/2309.05251/) (2023)
- [Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs](https://mlsanity.com/paper/2101.06894/) (2021)
- [Multi-View Transformer for 3D Visual Grounding](https://mlsanity.com/paper/2204.02174/) (2022)
- [LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent](https://mlsanity.com/paper/2309.12311/) (2023)
- [Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds](https://mlsanity.com/paper/2112.08879/) (2021)
- [Language Conditioned Spatial Relation Reasoning for 3D Object Grounding](https://mlsanity.com/paper/2211.09646/) (2022)
- [Grounded 3D-LLM with Referent Tokens](https://mlsanity.com/paper/2405.10370/) (2024)
- [GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs](https://mlsanity.com/paper/2312.00093/) (2023)

## Built on by (most cited first, 27 of 27)

- [MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs](https://mlsanity.com/paper/2503.13111/) (2025)
- [Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks](https://mlsanity.com/paper/2510.25760/) (2025)
- [Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning](https://mlsanity.com/paper/2506.05341/) (2025)
- [Neural Brain: A Neuroscience-inspired Framework for Embodied Agents](https://mlsanity.com/paper/2505.07634/) (2025)
- [Object-Centric Representation Learning for Enhanced 3D Semantic Scene Graph Prediction](https://mlsanity.com/paper/2510.04714/) (2025)
- [3D Scene Graphs: Open Challenges and Future Directions](https://mlsanity.com/paper/2606.19383/) (2026)
- [Descrip3D: Enhancing Large Language Model-based 3D Scene Understanding with Object-Level Text Descriptions](https://mlsanity.com/paper/2507.14555/) (2025)
- [Open-Vocabulary Indoor Object Grounding with 3D Hierarchical Scene Graph](https://mlsanity.com/paper/2507.12123/) (2025)
- [The Semantic Lifecycle in Embodied AI: Acquisition, Representation and Storage via Foundation Models](https://mlsanity.com/paper/2601.08876/) (2026)
- [SoPE: Spherical Coordinate-Based Positional Embedding for Enhancing Spatial Perception of 3D LVLMs](https://mlsanity.com/paper/2602.22716/) (2026)
- [SSR: Pushing the Limit of Spatial Intelligence with Structured Scene Reasoning](https://mlsanity.com/paper/2603.00409/) (2026)
- [Proxy3D: Efficient 3D Representations for Vision-Language Models via Semantic Clustering and Alignment](https://mlsanity.com/paper/2605.08064/) (2026)
- [Selective Synergistic Learning for Video Object-Centric Learning](https://mlsanity.com/paper/2606.15527/) (2026)
- [M3DMap: Object-aware Multimodal 3D Mapping for Dynamic Environments](https://mlsanity.com/paper/2508.17044/) (2025)
- [Spatiotemporal Knowledge Graphs as Persistent Scene Memory for Embodied Question Answering](https://mlsanity.com/paper/2510.01483/) (2025)
- [Scalable Object Relation Encoding for Better 3D Spatial Reasoning in Large Language Models](https://mlsanity.com/paper/2603.24721/) (2026)
- [Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrieval](https://mlsanity.com/paper/2604.15951/) (2026)
- [PAR3D: A Unified 3D-MLLM with Part-Aware Representation for Scene Understanding](https://mlsanity.com/paper/2606.06485/) (2026)
- [DGA-Net: Enhancing SAM with Depth Prompting and Graph-Anchor Guidance for Camouflaged Object Detection](https://mlsanity.com/paper/2601.02831/) (2026)
- [SpatialPoint: Spatial-aware Point Prediction for Embodied Localization](https://mlsanity.com/paper/2603.26690/) (2026)
- [Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs](https://mlsanity.com/paper/2604.02689/) (2026)
- [Multi-Scale Gaussian-Language Map for Zero-shot Embodied Navigation and Reasoning](https://mlsanity.com/paper/2605.01736/) (2026)
- [Reasmory: 3D Reconstruction as Explicit Memory for VLMs Spatial Reasoning](https://mlsanity.com/paper/2606.00963/) (2026)
- [3D-PLOT-LLM: Part-Level Object Tokens for 3D Large Language Models](https://mlsanity.com/paper/2606.19828/) (2026)
- [Scaling Diverse Language Generation for 3D Visual Grounding](https://mlsanity.com/paper/2606.20946/) (2026)
- [CAIRN: Cross-Room 3D Scene Understanding with Topology-Aware Large Multimodal Models](https://mlsanity.com/paper/2607.06534/) (2026)
- [Token-Budgeted Candidate Retrieval for 3D Scene-Grounded VLMs: Category Names vs. Pairwise Geometry](https://mlsanity.com/paper/2610.14207/) (2026)

## Abstract (arXiv)

A 3D scene graph represents a compact scene model by capturing both the objects present and the semantic relationships between them, making it a promising structure for robotic applications. To effectively interact with users, an embodied intelligent agent should be able to answer a wide range of natural language queries about the surrounding 3D environment. Large Language Models (LLMs) are beneficial solutions for user-robot interaction due to their natural language understanding and reasoning abilities. Recent methods for learning scene representations have shown that adapting these representations to the 3D world can significantly improve the quality of LLM responses. However, existing methods typically rely only on geometric information, such as object coordinates, and overlook the rich semantic relationships between objects. In this work, we propose 3DGraphLLM, a method for constructing a learnable representation of a 3D scene graph that explicitly incorporates semantic relationships. This representation is used as input to LLMs for performing 3D vision-language tasks. In our experiments on popular ScanRefer, Multi3DRefer, ScanQA, Sqa3D, and Scan2cap datasets, we demonstrate that our approach outperforms baselines that do not leverage semantic relationships between objects. The code is publicly available at https://github.com/CognitiveAISystems/3DGraphLLM.