DreamScene：基於3D高斯分佈的端到端文本到3D場景生成

摘要

從自然語言生成3D場景在遊戲、電影和設計領域具有巨大潛力。然而，現有方法在自動化、3D一致性和細粒度控制方面面臨挑戰。我們提出了DreamScene，這是一個從文本或對話生成高質量且可編輯3D場景的端到端框架。DreamScene始於場景規劃模塊，其中GPT-4代理推斷物體語義和空間約束，構建混合圖。基於圖的放置算法隨後生成結構化且無碰撞的佈局。根據此佈局，形成模式採樣（FPS）通過多時間步採樣和重建優化生成物體幾何，實現快速且逼真的合成。為確保全局一致性，DreamScene採用了一種針對室內外場景定制的漸進式相機採樣策略。最後，系統支持細粒度場景編輯，包括物體移動、外觀變化和4D動態運動。實驗表明，DreamScene在質量、一致性和靈活性上超越先前方法，為開放領域3D內容創作提供了實用解決方案。代碼和演示可在https://jahnsonblack.github.io/DreamScene-Full/獲取。

English

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/.

DreamScene：基於3D高斯分佈的端到端文本到3D場景生成

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

摘要

Support