We introduce a new approach to high-fidelity 3D scene reconstruction from multi-view RGB images that tightly couples reconstruction with a strong generative 3D prior. We cast scene reconstruction as conditional 3D generation over a set of spatially-localized, overlapping chunks that together tile the scene, scaling generation to large scene extents. Crucially, we inherit the fidelity and completeness of state-of-the-art generative shape models -- we use Trellis.2 as an example -- which we generalize to the scene level. To this end, we propose a projection-based conditioning mechanism that lifts posed multi-view image features into a coherent 3D representation aligned with the generative model, independent of view ordering and spatially anchored to the scene, yielding high-fidelity, multi-view consistent generated geometry. This enables lifting the strong object-level prior of Trellis.2 to multi-view, scene-scale generation, producing faithful, editable PBR mesh reconstructions of indoor environments. As a result, we obtain high-fidelity results that outperform cutting-edge reconstruction methods by 16%.

翻译：我们提出了一种从多视角RGB图像进行高保真三维场景重建的新方法，该方法将重建过程与强大的生成式三维先验紧密耦合。我们将场景重建建模为对一组空间局部化、相互重叠的区块进行条件化三维生成，这些区块共同覆盖整个场景，从而将生成扩展到大规模场景范围。关键之处在于，我们继承了最先进生成式形状模型（以Trellis.2为例）的保真度和完整性，并将其推广到场景级别。为此，我们提出了一种基于投影的条件化机制，该机制将带有位姿的多视角图像特征提升为与生成模型对齐的连贯三维表示，该表示独立于视角顺序且在空间上锚定于场景，从而生成高保真、多视角一致的几何结构。这使得Trellis.2强大的对象级先验得以提升到多视角、场景规模的生成，能够生成用于室内环境的高保真、可编辑的PBR网格重建结果。最终，我们获得的高保真结果在性能上超越了最先进的重建方法16%。