{"ID":2893138,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.13985","arxiv_id":"2507.13985","title":"DreamScene: 3D Gaussian-based End-to-end Text-to-3D Scene Generation","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/.","short_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 dialogu...","url_abs":"https://arxiv.org/abs/2507.13985","url_pdf":"https://arxiv.org/pdf/2507.13985v2","authors":"[\"Haoran Li\",\"Yuli Tian\",\"Kun Lan\",\"Yong Liao\",\"Lin Wang\",\"Pan Hui\",\"Peng Yuan Zhou\"]","published":"2025-07-18T14:45:54Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}