长尾互联网照片重建
Long-Tail Internet Photo Reconstruction
从已重建的互联网地标中采样稀疏子集来模拟长尾场景的相机分布，为稀疏视角三维重建提供了一种可扩展的监督构造方式；该思路可直接用于微调现有三维基础模型，提升极端稀疏与对称重复场景下的重建鲁棒性。
原文依据 it can be effectively simulated by sampling sparse subsets from well-reconstructed Internet landmarks
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论互联网照片集合呈现出极端的长尾分布：少数著名地标被密集拍摄并易于三维重建，而大多数真实场景仅由稀疏、含噪且分布不均的影像所表示，超出了经典方法与学习型三维方法的能力范围。我们认为，处理这一长尾情形是三维基础模型的下一个前沿方向之一。尽管从稀疏场景中获取可靠的真值三维监督十分困难，但我们观察到，可以通过从重建良好的互联网地标中采样稀疏子集来有效模拟这种监督。为此，我们提出了 MegaDepth-X，一个包含干净稠密深度的大规模三维重建数据集，并给出了一种采样训练图像集合的策略，以模拟长尾场景中的相机分布。利用这些组件对三维基础模型进行微调，可在极端稀疏条件下获得鲁棒的重建，同时也能在对称与重复场景中实现更可靠的重建，并保持对标准稠密三维基准数据集的泛化能力。
英文原文摘要 1100 字符
Internet photo collections exhibit an extremely long-tailed distribution: a few famous landmarks are densely photographed and easily reconstructed in 3D, while most real-world sites are represented with sparse, noisy, uneven imagery beyond the capabilities of both classical and learned 3D methods. We believe that tackling this long-tail regime represents one of the next frontiers for 3D foundation models. Although reliable ground-truth 3D supervision from sparse scenes is challenging to acquire, we observe that it can be effectively simulated by sampling sparse subsets from well-reconstructed Internet landmarks. To this end, we introduce MegaDepth-X, a large dataset of 3D reconstructions with clean, dense depth, together with a strategy for sampling sets of training images that mimic camera distributions in long-tail scenes. Finetuning 3D foundation models with these components yields robust reconstructions under extreme sparsity, and also enables more reliable reconstruction in symmetric and repetitive scenes, while preserving generalization to standard, dense 3D benchmark datasets.