Modeling large scenes from unconstrained images has proven to be a major challenge in computer vision. Existing methods tackling in-the-wild scene modeling operate in closed-world settings, where no conditioning on priors acquired from real-world images is present. We propose RefinedFields, which is, to the best of our knowledge, the first method leveraging pre-trained models to improve in-the-wild scene modeling. We employ pre-trained networks to refine K-Planes representations via optimization guidance using an alternating training procedure. We carry out extensive experiments and verify the merit of our method on synthetic data and real tourism photo collections. RefinedFields enhances rendered scenes with richer details and outperforms previous work on the task of novel view synthesis in the wild. Our project page can be found at https://refinedfields.github.io .

翻译：从无约束图像中建模大场景已被证明是计算机视觉中的重大挑战。现有针对野外场景建模的方法在封闭世界设置下运行，未利用从真实世界图像中获取的先验知识进行条件约束。我们提出RefinedFields，据我们所知，这是首个利用预训练模型改进野外场景建模的方法。我们采用预训练网络，通过交替训练过程中的优化引导来精细化K-Planes表示。我们进行了大量实验，在合成数据和真实旅游照片集上验证了该方法的有效性。RefinedFields渲染的场景细节更丰富，在野外新视角合成任务上优于先前工作。项目页面请访问https://refinedfields.github.io。