3DCity-LLM: Empowering Multi-modality Large Language Models for 3D City-scale Perception and Understanding

• URL: http://arxiv.org/abs/2603.23447v1
• Date: Tue, 24 Mar 2026 17:18:44 GMT
• Title: 3DCity-LLM: Empowering Multi-modality Large Language Models for 3D City-scale Perception and Understanding
• Abstract summary: 3DCity-LLM is a unified framework designed for 3D city-scale vision-language perception and understanding.<n>This dataset comprises approximately 1.2 million high-quality samples across seven representative task categories.<n>Experiments on two benchmarks demonstrate that 3DCity-LLM significantly outperforms existing state-of-the-art methods.
• Score: 23.008584023129703
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While multi-modality large language models excel in object-centric or indoor scenarios, scaling them to 3D city-scale environments remains a formidable challenge. To bridge this gap, we propose 3DCity-LLM, a unified framework designed for 3D city-scale vision-language perception and understanding. 3DCity-LLM employs a coarse-to-fine feature encoding strategy comprising three parallel branches for target object, inter-object relationship, and global scene. To facilitate large-scale training, we introduce 3DCity-LLM-1.2M dataset that comprises approximately 1.2 million high-quality samples across seven representative task categories, ranging from fine-grained object analysis to multi-faceted scene planning. This strictly quality-controlled dataset integrates explicit 3D numerical information and diverse user-oriented simulations, enriching the question-answering diversity and realism of urban scenarios. Furthermore, we apply a multi-dimensional protocol based on text-similarity metrics and LLM-based semantic assessment to ensure faithful and comprehensive evaluations for all methods. Extensive experiments on two benchmarks demonstrate that 3DCity-LLM significantly outperforms existing state-of-the-art methods, offering a promising and meaningful direction for advancing spatial reasoning and urban intelligence. The source code and dataset are available at https://github.com/SYSU-3DSTAILab/3D-City-LLM.

Related papers

• Abstract 3D Perception for Spatial Intelligence in Vision-Language Models [100.13033631690114]
  Vision-language models (VLMs) struggle with 3D-related tasks such as spatial cognition and physical understanding.<n>We introduce SandboxVLM, a framework that leverages abstract bounding boxes to encode geometric structure and physical kinematics for VLM.<n>Our approach consistently improves spatial intelligence, achieving an 8.3% gain on SAT Real compared with baseline methods.
  arXiv  Detail & Related papers  (2025-11-14T04:16:09Z)
• MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs [19.70116190496693]
  Multimodal large language models (MLLMs) excel at 2D visual understanding but remain limited in their ability to reason about 3D space.<n>In this work, we leverage large-scale high-quality 3D scene data with open-set annotations to introduce 1) a novel supervised fine-tuning dataset and 2) a new evaluation benchmark, focused on indoor scenes.
  arXiv  Detail & Related papers  (2025-03-17T12:34:22Z)
• 3UR-LLM: An End-to-End Multimodal Large Language Model for 3D Scene Understanding [49.15555885075644]
  We develop pipeline based on open-source 2D MLLMs and LLMs to generate high-quality 3D-text pairs.<n>We introduce the 3UR-LLM model, an end-to-end 3D MLLM designed for precise interpretation of 3D scenes.
  arXiv  Detail & Related papers  (2025-01-14T03:50:23Z)
• 3D Question Answering for City Scene Understanding [12.433903847890322]
  3D multimodal question answering (MQA) plays a crucial role in scene understanding by enabling intelligent agents to comprehend their surroundings in 3D environments. We introduce a novel 3D MQA dataset named City-3DQA for city-level scene understanding. A new benchmark is reported and our proposed Sg-CityU achieves accuracy of 63.94 % and 63.76 % in different settings of City-3DQA.
  arXiv  Detail & Related papers  (2024-07-24T16:22:27Z)
• 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)
• MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations [55.022519020409405]
  This paper builds the first largest ever multi-modal 3D scene dataset and benchmark with hierarchical grounded language annotations, MMScan.<n>The resulting multi-modal 3D dataset encompasses 1.4M meta-annotated captions on 109k objects and 7.7k regions as well as over 3.04M diverse samples for 3D visual grounding and question-answering benchmarks.
  arXiv  Detail & Related papers  (2024-06-13T17:59:30Z)
• 3DBench: A Scalable 3D Benchmark and Instruction-Tuning Dataset [13.808860456901204]
  We introduce a scalable 3D benchmark, accompanied by a large-scale instruction-tuning dataset known as 3DBench. Specifically, we establish the benchmark that spans a wide range of spatial and semantic scales, from object-level to scene-level. We present a rigorous pipeline for automatically constructing scalable 3D instruction-tuning datasets, covering 10 diverse multi-modal tasks with more than 0.23 million QA pairs generated in total.
  arXiv  Detail & Related papers  (2024-04-23T02:06:10Z)
• Volumetric Environment Representation for Vision-Language Navigation [66.04379819772764]
  Vision-language navigation (VLN) requires an agent to navigate through a 3D environment based on visual observations and natural language instructions. We introduce a Volumetric Environment Representation (VER), which voxelizes the physical world into structured 3D cells. VER predicts 3D occupancy, 3D room layout, and 3D bounding boxes jointly.
  arXiv  Detail & Related papers  (2024-03-21T06:14:46Z)
• Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D Representation [72.94143731623117]
  Existing methods simply align 3D representations with single-view 2D images and coarse-grained parent category text. Insufficient synergy neglects the idea that a robust 3D representation should align with the joint vision-language space. We propose a multi-view joint modality modeling approach, termed JM3D, to obtain a unified representation for point cloud, text, and image.
  arXiv  Detail & Related papers  (2023-08-06T01:11:40Z)
• ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding [96.95120198412395]
  We introduce tri-modal pre-training framework that automatically generates holistic language descriptions for 3D shapes. It only needs 3D data as input, eliminating the need for any manual 3D annotations, and is therefore scalable to large datasets. We conduct experiments on two large-scale 3D datasets, NN and ShapeNet, and augment them with tri-modal datasets of 3D point clouds, captioning, and language for training. Experiments show that NN-2 demonstrates substantial benefits in three downstream tasks: zero-shot 3D classification, standard 3D classification with finetuning, and 3D (3D
  arXiv  Detail & Related papers  (2023-05-14T23:14:09Z)

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.