ReconFusion: 3D Reconstruction with Diffusion Priors
This addresses the time-consuming capture process for 3D reconstruction in computer vision applications.
The paper tackles the problem of 3D reconstruction requiring many input images by proposing ReconFusion, which uses a diffusion prior to reconstruct scenes from only a few photos, achieving significant performance improvements over previous few-view methods.
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.