Long-Tail Internet Photo Reconstruction

Pretrained 𝜋 3 Ours Pretrained 𝜋 3 Ours Scene (sorted by #images) Registered images Total images #images per Scene Long Tail Duomo (Cagliari) -Crypt Calvaire de Plougonven Figure 1. Long-tail Internet photo reconstruction. Internet photo collections follow a long-tailed distribution. In the top plot, the x-axis represents scene index (sorted by image count) and the y-axis shows images per scene (scenes are drawn from MegaScenes [36], a dataset of Internet photo collections). The light blue curve plots the total number of Internet photos per scene, while the steel blue curve shows the size of the subset of photos that were successfully registered using SfM. The head of this distribution of photo collections represents well-photographed scenes; here, there are 6,985 scenes with >50 registered images. However, most photo collections are in the long tail of this distribution; here, 418,056 scenes with fewer than 50 registered photos. State-of-the-art methods often fail on scenes in this tail. In the lower half of the figure, we show two examples from the long tail, along with representative input images and the corresponding reconstructions.

On Calvaire de Plougonven, COLMAP doesn't register any image; on both Duomo (Cagliari)-Crypt and Calvaire de Plougonven, recent feed-forward reconstruction models like π 3 [44] produce poor results. We propose MegaDepth-X dataset and a strategy for mimicking long-tail camera distributions, on which fine-tuned models like π 3 exhibit better reconstruction robustness.