Abstract
We introduce MVRoom, a controllable novel view synthesis (NVS) pipeline for 3D indoor scenes that uses multi-view diffusion conditioned on a coarse 3D layout. MVRoom employs a two-stage design in which the 3D layout is used throughout to enforce multi-view consistency. The first stage employs novel representations to effectively bridge the 3D layout and consistent image-based condition signals for multi-view generation. The second stage performs image-conditioned multi-view generation, incorporating a layout-aware epipolar attention mechanism to enhance multi-view consistency during the diffusion process. Additionally, we introduce an iterative framework that generates 3D scenes with varying numbers of objects and scene complexities by recursively performing multi-view generation (MVRoom), supporting text-to-scene generation. Experimental results demonstrate that our approach achieves high-fidelity and controllable 3D scene generation for NVS, outperforming state-of-the-art baseline methods both quantitatively and qualitatively. Ablation studies further validate the effectiveness of key components within our generation pipeline.
Abstract (translated)
我们介绍了MVRoom，这是一种用于室内三维场景的可控新颖视角合成（NVS）流水线，它使用基于粗略3D布局的多视图扩散。MVRoom采用两阶段设计，在整个过程中利用3D布局来强制执行多视图一致性。第一阶段采用了新的表示方法，有效地将3D布局与一致的图像条件信号结合起来，用于多视图生成。第二阶段进行受图像条件限制的多视图生成，并引入了一种具有视角意识的极线注意力机制，在扩散过程中增强多视图的一致性。 此外，我们还介绍了一个迭代框架，该框架通过递归执行多视图生成（MVRoom）来生成包含不同数量对象和场景复杂度的3D场景，支持从文本到场景的生成。实验结果表明，我们的方法在NVS方面实现了高质量且可控的三维场景生成，在定量和定性评估中均优于现有的基准方法。消融研究进一步验证了我们生成管道中关键组件的有效性。
URL
https://arxiv.org/abs/2512.04248
