Agentic 3D Scene Generation with Spatially Contextualized VLMs

• URL: http://arxiv.org/abs/2505.20129v3
• Date: Fri, 04 Jul 2025 15:28:37 GMT
• Title: Agentic 3D Scene Generation with Spatially Contextualized VLMs
• Authors: Xinhang Liu, Yu-Wing Tai, Chi-Keung Tang,
• Abstract summary: We introduce a new paradigm that enables vision-language models to generate, understand, and edit complex 3D environments.<n>We develop an agentic 3D scene generation pipeline in which the VLM iteratively reads from and updates the spatial context.<n>Results show that our framework can handle diverse and challenging inputs, achieving a level of generalization not observed in prior work.
• Score: 67.31920821192323
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Despite recent advances in multimodal content generation enabled by vision-language models (VLMs), their ability to reason about and generate structured 3D scenes remains largely underexplored. This limitation constrains their utility in spatially grounded tasks such as embodied AI, immersive simulations, and interactive 3D applications. We introduce a new paradigm that enables VLMs to generate, understand, and edit complex 3D environments by injecting a continually evolving spatial context. Constructed from multimodal input, this context consists of three components: a scene portrait that provides a high-level semantic blueprint, a semantically labeled point cloud capturing object-level geometry, and a scene hypergraph that encodes rich spatial relationships, including unary, binary, and higher-order constraints. Together, these components provide the VLM with a structured, geometry-aware working memory that integrates its inherent multimodal reasoning capabilities with structured 3D understanding for effective spatial reasoning. Building on this foundation, we develop an agentic 3D scene generation pipeline in which the VLM iteratively reads from and updates the spatial context. The pipeline features high-quality asset generation with geometric restoration, environment setup with automatic verification, and ergonomic adjustment guided by the scene hypergraph. Experiments show that our framework can handle diverse and challenging inputs, achieving a level of generalization not observed in prior work. Further results demonstrate that injecting spatial context enables VLMs to perform downstream tasks such as interactive scene editing and path planning, suggesting strong potential for spatially intelligent systems in computer graphics, 3D vision, and embodied applications. Project page: https://spatctxvlm.github.io/project_page/.

Related papers

• ReSem3D: Refinable 3D Spatial Constraints via Fine-Grained Semantic Grounding for Generalizable Robotic Manipulation [12.059517583878756]
  We propose ReSem3D, a unified manipulation framework for semantically diverse environments.<n>We show that ReSem3D performs diverse manipulation tasks under zero-shot conditions, exhibiting strong adaptability and generalization.
  arXiv  Detail & Related papers  (2025-07-24T10:07:31Z)
• Object-X: Learning to Reconstruct Multi-Modal 3D Object Representations [112.29763628638112]
  Object-X is a versatile multi-modal 3D representation framework.<n>It can encoding rich object embeddings and decoding them back into geometric and visual reconstructions.<n>It supports a range of downstream tasks, including scene alignment, single-image 3D object reconstruction, and localization.
  arXiv  Detail & Related papers  (2025-06-05T09:14:42Z)
• Spatial Understanding from Videos: Structured Prompts Meet Simulation Data [79.52833996220059]
  We present a unified framework for enhancing 3D spatial reasoning in pre-trained vision-language models without modifying their architecture.<n>This framework combines SpatialMind, a structured prompting strategy that decomposes complex scenes and questions into interpretable reasoning steps, with ScanForgeQA, a scalable question-answering dataset built from diverse 3D simulation scenes.
  arXiv  Detail & Related papers  (2025-06-04T07:36:33Z)
• Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence [13.168559963356952]
  We present Spatial-MLLM, a novel framework for visual-based spatial reasoning from purely 2D observations.<n>Our key insight is to unleash the strong structure prior to the feed-forward visual geometry foundation model.<n>A connector then integrates both features into unified visual tokens for enhanced spatial understanding.
  arXiv  Detail & Related papers  (2025-05-29T17:59:04Z)
• VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction [86.82819259860186]
  We introduce VLM-3R, a unified framework for Vision-Language Models (VLMs) that incorporates 3D Reconstructive instruction tuning.<n>VLM-3R processes monocular video frames by employing a geometry encoder to derive implicit 3D tokens that represent spatial understanding.
  arXiv  Detail & Related papers  (2025-05-26T17:56:30Z)
• From Flight to Insight: Semantic 3D Reconstruction for Aerial Inspection via Gaussian Splatting and Language-Guided Segmentation [3.0477617036157136]
  High-fidelity 3D reconstruction is critical for aerial inspection tasks such as infrastructure monitoring, structural assessment, and environmental surveying.<n>While traditional photogrammetry techniques enable geometric modeling, they lack semantic interpretability, limiting their effectiveness for automated inspection.<n>Recent advances in neural rendering and 3D Gaussian Splatting (3DGS) offer efficient, photorealistic reconstructions but similarly lack scene-level understanding.<n>We present a UAV-based pipeline that extends Feature-3DGS for language-guided 3D segmentation.
  arXiv  Detail & Related papers  (2025-05-23T02:35:46Z)
• HiScene: Creating Hierarchical 3D Scenes with Isometric View Generation [50.206100327643284]
  HiScene is a novel hierarchical framework that bridges the gap between 2D image generation and 3D object generation.<n>We generate 3D content that aligns with 2D representations while maintaining compositional structure.
  arXiv  Detail & Related papers  (2025-04-17T16:33:39Z)
• LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models [57.92316645992816]
  Spatial reasoning is a fundamental aspect of human cognition, enabling intuitive understanding and manipulation of objects in three-dimensional space.<n>We introduce LayoutVLM, a framework and scene layout representation that exploits the semantic knowledge of Vision-Language Models (VLMs)<n>We demonstrate that fine-tuning VLMs with the proposed scene layout representation extracted from existing scene datasets can improve their reasoning performance.
  arXiv  Detail & Related papers  (2024-12-03T06:15:04Z)
• Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpainting [47.014044892025346]
  Architect is a generative framework that creates complex and realistic 3D embodied environments leveraging diffusion-based 2D image inpainting. Our pipeline is further extended to a hierarchical and iterative inpainting process to continuously generate placement of large furniture and small objects to enrich the scene.
  arXiv  Detail & Related papers  (2024-11-14T22:15:48Z)
• Dynamic Scene Understanding through Object-Centric Voxelization and Neural Rendering [57.895846642868904]
  We present a 3D generative model named DynaVol-S for dynamic scenes that enables object-centric learning.<n>voxelization infers per-object occupancy probabilities at individual spatial locations.<n>Our approach integrates 2D semantic features to create 3D semantic grids, representing the scene through multiple disentangled voxel grids.
  arXiv  Detail & Related papers  (2024-07-30T15:33:58Z)
• 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. 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)
• SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors [42.85605789984155]
  Current state-of-the-art spatial reasoning-enhanced VLMs are trained to excel at spatial visual question answering (VQA) We present SpatialPIN, a framework designed to enhance the spatial reasoning capabilities of VLMs through prompting and interacting with priors from multiple 3D foundation models in a zero-shot, training-free manner. Our spatial reasoning-imbued VLM performs well on various forms of spatial VQA and can extend to help in various downstream robotics tasks such as pick and stack and trajectory planning.
  arXiv  Detail & Related papers  (2024-03-18T17:38:29Z)

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.