Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation

• URL: http://arxiv.org/abs/2505.02836v1
• Date: Mon, 05 May 2025 17:59:58 GMT
• Title: Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation
• Authors: Lu Ling, Chen-Hsuan Lin, Tsung-Yi Lin, Yifan Ding, Yu Zeng, Yichen Sheng, Yunhao Ge, Ming-Yu Liu, Aniket Bera, Zhaoshuo Li,
• Abstract summary: Scenethesis is a framework that integrates text-based scene planning with vision-guided layout refinement.<n>It generates diverse, realistic, and physically plausible 3D interactive scenes, making it valuable for virtual content creation, simulation environments, and embodied AI research.
• Score: 36.44409268300039
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Synthesizing interactive 3D scenes from text is essential for gaming, virtual reality, and embodied AI. However, existing methods face several challenges. Learning-based approaches depend on small-scale indoor datasets, limiting the scene diversity and layout complexity. While large language models (LLMs) can leverage diverse text-domain knowledge, they struggle with spatial realism, often producing unnatural object placements that fail to respect common sense. Our key insight is that vision perception can bridge this gap by providing realistic spatial guidance that LLMs lack. To this end, we introduce Scenethesis, a training-free agentic framework that integrates LLM-based scene planning with vision-guided layout refinement. Given a text prompt, Scenethesis first employs an LLM to draft a coarse layout. A vision module then refines it by generating an image guidance and extracting scene structure to capture inter-object relations. Next, an optimization module iteratively enforces accurate pose alignment and physical plausibility, preventing artifacts like object penetration and instability. Finally, a judge module verifies spatial coherence. Comprehensive experiments show that Scenethesis generates diverse, realistic, and physically plausible 3D interactive scenes, making it valuable for virtual content creation, simulation environments, and embodied AI research.

Related papers

• SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes [105.8644620467576]
  We introduce Stextscurprise3D, a novel dataset designed to evaluate language-guided spatial reasoning segmentation in complex 3D scenes.<n>Stextscurprise3D consists of more than 200k vision language pairs across 900+ detailed indoor scenes from ScanNet++ v2.<n>The dataset contains 89k+ human-annotated spatial queries deliberately crafted without object name.
  arXiv  Detail & Related papers  (2025-07-10T14:01:24Z)
• A Neural Representation Framework with LLM-Driven Spatial Reasoning for Open-Vocabulary 3D Visual Grounding [78.99798110890157]
  Open-vocabulary 3D visual grounding aims to localize target objects based on free-form language queries.<n>Existing language field methods struggle to accurately localize instances using spatial relations in language queries.<n>We propose SpatialReasoner, a novel neural representation-based framework with large language model (LLM)-driven spatial reasoning.
  arXiv  Detail & Related papers  (2025-07-09T10:20:38Z)
• Video Perception Models for 3D Scene Synthesis [109.5543506037003]
  VIPScene is a novel framework that exploits the encoded commonsense knowledge of the 3D physical world in video generation models.<n>VIPScene seamlessly integrates video generation, feedforward 3D reconstruction, and open-vocabulary perception models to semantically and geometrically analyze each object in a scene.
  arXiv  Detail & Related papers  (2025-06-25T16:40:17Z)
• ReSpace: Text-Driven 3D Scene Synthesis and Editing with Preference Alignment [1.0918065824771606]
  ReSpace is a generative framework for text-driven 3D indoor scene synthesis and editing.<n>We leverage a dual-stage training approach combining supervised fine-tuning and preference alignment.<n>For scene editing, we employ a zero-shot LLM to handle object removal and prompts for addition.
  arXiv  Detail & Related papers  (2025-06-03T05:22:04Z)
• Agentic 3D Scene Generation with Spatially Contextualized VLMs [67.31920821192323]
  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.
  arXiv  Detail & Related papers  (2025-05-26T15:28:17Z)
• 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)
• 3D Vision and Language Pretraining with Large-Scale Synthetic Data [28.45763758308814]
  3D Vision-Language Pre-training aims to provide a pre-train model which can bridge 3D scenes with natural language. We construct SynVL3D, a comprehensive synthetic scene-text corpus with 10K indoor scenes and 1M descriptions at object, view, and room levels. We propose a synthetic-to-real domain adaptation in downstream task fine-tuning process to address the domain shift.
  arXiv  Detail & Related papers  (2024-07-08T16:26:52Z)
• DreamScape: 3D Scene Creation via Gaussian Splatting joint Correlation Modeling [23.06464506261766]
  We present DreamScape, a method for generating 3D scenes from text.<n>We use 3D Gaussian Guide that encodes semantic primitives, spatial transformations and relationships from text using LLMs.<n>DreamScape achieves state-of-the-art performance, enabling high-fidelity, controllable 3D scene generation.
  arXiv  Detail & Related papers  (2024-04-14T12:13:07Z)
• Set-the-Scene: Global-Local Training for Generating Controllable NeRF Scenes [68.14127205949073]
  We propose a novel GlobalLocal training framework for synthesizing a 3D scene using object proxies. We show that using proxies allows a wide variety of editing options, such as adjusting the placement of each independent object. Our results show that Set-the-Scene offers a powerful solution for scene synthesis and manipulation.
  arXiv  Detail & Related papers  (2023-03-23T17:17:29Z)
• CLIP$^2$: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data [80.42480679542697]
  We propose Contrastive Language-Image-Point Cloud Pretraining (CLIP$2$) to learn the transferable 3D point cloud representation in realistic scenarios. Specifically, we exploit naturally-existed correspondences in 2D and 3D scenarios, and build well-aligned and instance-based text-image-point proxies from those complex scenarios.
  arXiv  Detail & Related papers  (2023-03-22T09:32:45Z)
• Object Scene Representation Transformer [56.40544849442227]
  We introduce Object Scene Representation Transformer (OSRT), a 3D-centric model in which individual object representations naturally emerge through novel view synthesis. OSRT scales to significantly more complex scenes with larger diversity of objects and backgrounds than existing methods. It is multiple orders of magnitude faster at compositional rendering thanks to its light field parametrization and the novel Slot Mixer decoder.
  arXiv  Detail & Related papers  (2022-06-14T15:40:47Z)
• Neural Rendering in a Room: Amodal 3D Understanding and Free-Viewpoint Rendering for the Closed Scene Composed of Pre-Captured Objects [40.59508249969956]
  We present a novel solution to mimic such human perception capability based on a new paradigm of amodal 3D scene understanding with neural rendering for a closed scene. We first learn the prior knowledge of the objects in a closed scene via an offline stage, which facilitates an online stage to understand the room with unseen furniture arrangement. During the online stage, given a panoramic image of the scene in different layouts, we utilize a holistic neural-rendering-based optimization framework to efficiently estimate the correct 3D scene layout and deliver realistic free-viewpoint rendering.
  arXiv  Detail & Related papers  (2022-05-05T15:34:09Z)
• Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering [42.37007176376849]
  We present a novel neural scene rendering system, which learns an object-compositional neural radiance field and produces realistic rendering for a clustered and real-world scene. To survive the training in heavily cluttered scenes, we propose a scene-guided training strategy to solve the 3D space ambiguity in the occluded regions and learn sharp boundaries for each object.
  arXiv  Detail & Related papers  (2021-09-04T11:37:18Z)
• Visiting the Invisible: Layer-by-Layer Completed Scene Decomposition [57.088328223220934]
  Existing scene understanding systems mainly focus on recognizing the visible parts of a scene, ignoring the intact appearance of physical objects in the real-world. In this work, we propose a higher-level scene understanding system to tackle both visible and invisible parts of objects and backgrounds in a given scene.
  arXiv  Detail & Related papers  (2021-04-12T11:37:23Z)
• SceneGen: Generative Contextual Scene Augmentation using Scene Graph Priors [3.1969855247377827]
  We introduce SceneGen, a generative contextual augmentation framework that predicts virtual object positions and orientations within existing scenes. SceneGen takes a semantically segmented scene as input, and outputs positional and orientational probability maps for placing virtual content. We formulate a novel spatial Scene Graph representation, which encapsulates explicit topological properties between objects, object groups, and the room. To demonstrate our system in action, we develop an Augmented Reality application, in which objects can be contextually augmented in real-time.
  arXiv  Detail & Related papers  (2020-09-25T18:36:27Z)

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.