DreamScape：基于Gaussian Splatting联合相关性建模的3D场景创建
DreamScape: 3D Scene Creation via Gaussian Splatting joint Correlation Modeling
AI总结：
提出DreamScape方法，利用Gaussian Splatting和LLM编码的3D Gaussian Guide实现局部到全局优化，解决多物体3D场景生成中的训练不稳定和物理碰撞问题，达到最先进的高保真可控生成效果。
摘要：
文本到3D创建的最新进展将Diffusion Models在文本到图像生成中的强大先验整合到3D领域。然而，生成具有多个物体的3D场景仍然具有挑战性。因此，我们提出了DreamScape，一种从文本生成3D场景的方法。利用Gaussian Splatting进行3D表示，DreamScape引入了3D Gaussian Guide，使用LLM从文本中编码语义原语、空间变换和关系，实现局部到全局的优化。在局部物体生成过程中采用渐进式尺度控制，解决全局优化阶段因简单混合而引发的训练不稳定问题。物体间的碰撞关系在全局层面进行建模，以减轻LLM先验的偏差，确保物理正确性。此外，为了生成如雨雪等广泛分布在场景中的普遍物体，我们设计了专门的稀疏初始化和致密化策略。实验表明，DreamScape实现了最先进的性能，能够生成高保真、可控的3D场景。
英文摘要：
Recent advances in text-to-3D creation integrate the potent prior of Diffusion Models from text-to-image generation into 3D domain. Nevertheless, generating 3D scenes with multiple objects remains challenging. Therefore, we present DreamScape, a method for generating 3D scenes from text. Utilizing Gaussian Splatting for 3D representation, DreamScape introduces 3D Gaussian Guide that encodes semantic primitives, spatial transformations and relationships from text using LLMs, enabling local-to-global optimization. Progressive scale control is tailored during local object generation, addressing training instability issue arising from simple blending in the global optimization stage. Collision relationships between objects are modeled at the global level to mitigate biases in LLMs priors, ensuring physical correctness. Additionally, to generate pervasive objects like rain and snow distributed extensively across the scene, we design specialized sparse initialization and densification strategy. Experiments demonstrate that DreamScape achieves state-of-the-art performance, enabling high-fidelity, controllable 3D scene generation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
