3D reconstruction methods such as Neural Radiance Fields (NeRFs) excel at rendering photorealistic novel views of complex scenes. However, recovering a high-quality NeRF typically requires tens to hundreds of input images, resulting in a time-consuming capture process. We present ReconFusion to reconstruct real-world scenes using only a few photos. Our approach leverages a diffusion prior for novel view synthesis, trained on synthetic and multiview datasets, which regularizes a NeRF-based 3D reconstruction pipeline at novel camera poses beyond those captured by the set of input images. Our method synthesizes realistic geometry and texture in underconstrained regions while preserving the appearance of observed regions. We perform an extensive evaluation across various real-world datasets, including forward-facing and 360-degree scenes, demonstrating significant performance improvements over previous few-view NeRF reconstruction approaches.

使用少量照片重建现实场景的方法，通过在合成和多视图数据集上训练的扩散先验来对新视角的合成进行规范化，从而在超约束区域综合出逼真的几何和纹理，同时保持观察区域的外观。与以前的少视图 NeRF 重建方法相比，我们在各种真实世界数据集上进行了广泛评估，包括正向和360度场景，并展示了显著的性能改进。

ReconFusion：基于扩散先验的三维重建