Long-tail Internet photo reconstruction
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 ...
| Authors | Yuan Li, Yuanbo Xiangli, Hadar Averbuch-Elor et al. |
|---|---|
| Primary category | cs.CV |
| Published | 24 April 2026 |
| Last updated at source | 24 April 2026 |
Connected in the knowledge graph
- y-u-a-n-l-i/MegaDepth-XDataset · cited by
Models and datasets referencing this paper
- y-u-a-n-l-i/MegaDepth-XDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.