DreamScene: 3D Gaussian-based End-to-end Text-to-3D Scene Generation

• URL: http://arxiv.org/abs/2507.13985v2
• Date: Tue, 29 Jul 2025 14:29:36 GMT
• Title: DreamScene: 3D Gaussian-based End-to-end Text-to-3D Scene Generation
• Authors: Haoran Li, Yuli Tian, Kun Lan, Yong Liao, Lin Wang, Pan Hui, Peng Yuan Zhou,
• Abstract summary: We present DreamScene, an end-to-end framework for high-quality and editable 3D scene generation from text or dialogue.<n>To ensure global consistent, DreamScene employs a progressive camera sampling strategy tailored to both indoor and outdoor settings.<n>Experiments demonstrate that DreamScene surpasses prior methods in quality, consistency, and flexibility.
• Score: 19.817968922757007
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generating 3D scenes from natural language holds great promise for applications in gaming, film, and design. However, existing methods struggle with automation, 3D consistency, and fine-grained control. We present DreamScene, an end-to-end framework for high-quality and editable 3D scene generation from text or dialogue. DreamScene begins with a scene planning module, where a GPT-4 agent infers object semantics and spatial constraints to construct a hybrid graph. A graph-based placement algorithm then produces a structured, collision-free layout. Based on this layout, Formation Pattern Sampling (FPS) generates object geometry using multi-timestep sampling and reconstructive optimization, enabling fast and realistic synthesis. To ensure global consistent, DreamScene employs a progressive camera sampling strategy tailored to both indoor and outdoor settings. Finally, the system supports fine-grained scene editing, including object movement, appearance changes, and 4D dynamic motion. Experiments demonstrate that DreamScene surpasses prior methods in quality, consistency, and flexibility, offering a practical solution for open-domain 3D content creation. Code and demos are available at https://jahnsonblack.github.io/DreamScene-Full/.

Related papers

• Scene Co-pilot: Procedural Text to Video Generation with Human in the Loop [32.92038804110175]
  Scene Copilot is a framework combining large language models (LLMs) with a procedural 3D scene generator.<n>Scene Codex is designed to translate textual user input into commands understandable by the 3D scene generator.<n> BlenderGPT provides users with an intuitive and direct way to precisely control the generated 3D scene and the final output video.
  arXiv  Detail & Related papers  (2024-11-26T19:21:57Z)
• SceneDreamer360: Text-Driven 3D-Consistent Scene Generation with Panoramic Gaussian Splatting [53.32467009064287]
  We propose a text-driven 3D-consistent scene generation model: SceneDreamer360. Our proposed method leverages a text-driven panoramic image generation model as a prior for 3D scene generation. Our experiments demonstrate that SceneDreamer360 with its panoramic image generation and 3DGS can produce higher quality, spatially consistent, and visually appealing 3D scenes from any text prompt.
  arXiv  Detail & Related papers  (2024-08-25T02:56:26Z)
• 3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting [100.94916668527544]
  Existing methods solely focus on either 2D individual object or 3D global scene editing. We propose 3DitScene, a novel and unified scene editing framework. It enables seamless editing from 2D to 3D, allowing precise control over scene composition and individual objects.
  arXiv  Detail & Related papers  (2024-05-28T17:59:01Z)
• 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)
• DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Sampling [17.807481666320825]
  We propose a novel text-to-3D scene generation framework, DreamScene, to tackle the aforementioned three challenges mainly via two strategies. First, DreamScene employs Formation Pattern Sampling (FPS), a multi-timestep sampling strategy guided by the formation patterns of 3D objects, to form fast, semantically rich, and high-quality representations. Second, DreamScene employs a progressive three-stage camera sampling strategy, specifically designed for both indoor and outdoor settings, to effectively ensure object-environment integration and scene-wide 3D consistency.
  arXiv  Detail & Related papers  (2024-04-04T16:38:57Z)
• GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting [52.150502668874495]
  We present GALA3D, generative 3D GAussians with LAyout-guided control, for effective compositional text-to-3D generation. GALA3D is a user-friendly, end-to-end framework for state-of-the-art scene-level 3D content generation and controllable editing.
  arXiv  Detail & Related papers  (2024-02-11T13:40:08Z)
• SceneWiz3D: Towards Text-guided 3D Scene Composition [134.71933134180782]
  Existing approaches either leverage large text-to-image models to optimize a 3D representation or train 3D generators on object-centric datasets. We introduce SceneWiz3D, a novel approach to synthesize high-fidelity 3D scenes from text.
  arXiv  Detail & Related papers  (2023-12-13T18:59:30Z)
• LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes [52.31402192831474]
  Existing 3D scene generation models, however, limit the target scene to specific domain. We propose LucidDreamer, a domain-free scene generation pipeline. LucidDreamer produces highly-detailed Gaussian splats with no constraint on domain of the target scene.
  arXiv  Detail & Related papers  (2023-11-22T13:27:34Z)
• DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-aware Scene Synthesis [90.32352050266104]
  DisCoScene is a 3Daware generative model for high-quality and controllable scene synthesis. It disentangles the whole scene into object-centric generative fields by learning on only 2D images with the global-local discrimination. We demonstrate state-of-the-art performance on many scene datasets, including the challenging outdoor dataset.
  arXiv  Detail & Related papers  (2022-12-22T18:59:59Z)

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.