SynCity：無需訓練的3D世界生成

摘要

我們致力於解決從文本描述生成三維世界的挑戰。我們提出了SynCity，這是一種無需訓練和優化的方法，它結合了預訓練三維生成模型的幾何精確性和二維圖像生成器的藝術多樣性，以創建大規模、高質量的三維空間。儘管大多數三維生成模型以物體為中心，無法生成大規模世界，但我們展示了如何將三維和二維生成器結合起來，生成不斷擴展的場景。通過基於瓦片的方法，我們允許對場景的佈局和外觀進行細粒度控制。世界以瓦片為單位逐塊生成，每個新瓦片在其世界上下文中生成，然後與場景融合。SynCity生成引人入勝且沉浸式的場景，細節豐富且多樣性十足。

English

We address the challenge of generating 3D worlds from textual descriptions. We propose SynCity, a training- and optimization-free approach, which leverages the geometric precision of pre-trained 3D generative models and the artistic versatility of 2D image generators to create large, high-quality 3D spaces. While most 3D generative models are object-centric and cannot generate large-scale worlds, we show how 3D and 2D generators can be combined to generate ever-expanding scenes. Through a tile-based approach, we allow fine-grained control over the layout and the appearance of scenes. The world is generated tile-by-tile, and each new tile is generated within its world-context and then fused with the scene. SynCity generates compelling and immersive scenes that are rich in detail and diversity.

SynCity：無需訓練的3D世界生成

SynCity: Training-Free Generation of 3D Worlds

摘要

Support