RoomDesigner：编码锚点潜变量以实现风格一致且形状兼容的室内场景生成
RoomDesigner: Encoding Anchor-latents for Style-consistent and Shape-compatible Indoor Scene Generation
AI总结：
提出两阶段模型RoomDesigner，通过离散向量量化编码家具为锚点潜变量，结合Transformer自回归生成，实现风格一致且形状兼容的室内场景，支持交互编辑，在3D-Front数据集上优于现有方法。
摘要：
室内场景生成旨在在空间合理的布局内创建形状兼容、风格一致的家具布置。然而，大多数现有方法主要关注生成合理的家具布局，而未纳入与单个家具相关的具体细节。为解决此限制，我们提出了一种两阶段模型，通过将家具编码为锚点潜变量表示，将形状先验整合到室内场景生成中。在第一阶段，我们采用离散向量量化将家具编码为锚点潜变量。基于锚点潜变量表示，家具的形状和位置信息通过位置、尺寸、朝向、类别以及我们的锚点潜变量的拼接来表征。在第二阶段，我们利用Transformer模型自回归地预测室内场景。得益于整合所提出的锚点潜变量表示，我们的生成模型能够生成形状兼容且风格一致的家具布置，并合成多样形状的家具。此外，我们的方法支持多种人机交互应用，如风格一致的场景补全、物体不匹配校正以及可控的物体级编辑。在3D-Front数据集上的实验结果表明，与现有方法相比，我们的方法能够生成更一致且兼容的室内场景，即使没有形状检索。此外，广泛的消融研究证实了我们在室内场景生成模型中设计选择的有效性。
英文摘要：
Indoor scene generation aims at creating shape-compatible, style-consistent furniture arrangements within a spatially reasonable layout. However, most existing approaches primarily focus on generating plausible furniture layouts without incorporating specific details related to individual furniture pieces. To address this limitation, we propose a two-stage model integrating shape priors into the indoor scene generation by encoding furniture as anchor latent representations. In the first stage, we employ discrete vector quantization to encode furniture pieces as anchor-latents. Based on the anchor-latents representation, the shape and location information of the furniture was characterized by a concatenation of location, size, orientation, class, and our anchor latent. In the second stage, we leverage a transformer model to predict indoor scenes autoregressively. Thanks to incorporating the proposed anchor-latents representations, our generative model produces shape-compatible and style-consistent furniture arrangements and synthesis furniture in diverse shapes. Furthermore, our method facilitates various human interaction applications, such as style-consistent scene completion, object mismatch correction, and controllable object-level editing. Experimental results on the 3D-Front dataset demonstrate that our approach can generate more consistent and compatible indoor scenes compared to existing methods, even without shape retrieval. Additionally, extensive ablation studies confirm the effectiveness of our design choices in the indoor scene generation model.
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。
