NuiScene：探索无界户外场景的高效生成

NuiScene: Exploring Efficient Generation of Unbounded Outdoor Scenes

March 20, 2025

作者: Han-Hung Lee, Qinghong Han, Angel X. Chang

cs.AI

摘要

本文探讨了生成广阔户外场景的任务，涵盖从城堡到高层建筑的各种场景。与以往主要关注室内场景生成的研究不同，户外场景生成面临独特的挑战，包括场景高度的巨大差异以及需要一种能够快速生成大规模景观的方法。为此，我们提出了一种高效的方法，将场景块编码为统一的向量集，相较于先前方法中使用的空间结构化潜在表示，提供了更好的压缩和性能。此外，我们训练了一个显式的外延生成模型，用于无界生成，与之前基于重采样的修复方案相比，提高了场景的连贯性，同时通过消除额外的扩散步骤加速了生成过程。为了支持这一任务，我们精心制作了NuiScene43，这是一个规模虽小但质量上乘的场景集合，经过预处理以用于联合训练。值得注意的是，当在不同风格的场景上进行训练时，我们的模型能够在同一场景中融合不同的环境，如乡村房屋和城市摩天大楼，这凸显了我们的场景整理过程在利用异构场景进行联合训练方面的潜力。

English

In this paper, we explore the task of generating expansive outdoor scenes, ranging from castles to high-rises. Unlike indoor scene generation, which has been a primary focus of prior work, outdoor scene generation presents unique challenges, including wide variations in scene heights and the need for a method capable of rapidly producing large landscapes. To address this, we propose an efficient approach that encodes scene chunks as uniform vector sets, offering better compression and performance than the spatially structured latents used in prior methods. Furthermore, we train an explicit outpainting model for unbounded generation, which improves coherence compared to prior resampling-based inpainting schemes while also speeding up generation by eliminating extra diffusion steps. To facilitate this task, we curate NuiScene43, a small but high-quality set of scenes, preprocessed for joint training. Notably, when trained on scenes of varying styles, our model can blend different environments, such as rural houses and city skyscrapers, within the same scene, highlighting the potential of our curation process to leverage heterogeneous scenes for joint training.