# Long-tail Internet photo reconstruction

arXiv: https://arxiv.org/abs/2604.22714 · HTML: https://mlsanity.com/paper/2604.22714/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 49 references that are in the map.
- First posted on arXiv 24 Apr 2026.

## Builds on (most cited first, 28 of 28)

- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction](https://mlsanity.com/paper/2109.00512/) (2021)
- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [TartanAir: A Dataset to Push the Limits of Visual SLAM](https://mlsanity.com/paper/2003.14338/) (2020)
- [BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks](https://mlsanity.com/paper/1911.10127/) (2019)
- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass](https://mlsanity.com/paper/2501.13928/) (2025)
- [Neural RGB-D Surface Reconstruction](https://mlsanity.com/paper/2104.04532/) (2021)
- [DISK: Learning local features with policy gradient](https://mlsanity.com/paper/2006.13566/) (2020)
- [MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision](https://mlsanity.com/paper/2410.19115/) (2024)
- [3D Reconstruction with Spatial Memory](https://mlsanity.com/paper/2408.16061/) (2024)
- [ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals](https://mlsanity.com/paper/1905.02082/) (2019)
- [FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views](https://mlsanity.com/paper/2502.12138/) (2025)
- [MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion](https://mlsanity.com/paper/2409.19152/) (2024)
- [MegaScenes: Scene-Level View Synthesis at Scale](https://mlsanity.com/paper/2406.11819/) (2024)
- [OmniGlue: Generalizable Feature Matching with Foundation Model Guidance](https://mlsanity.com/paper/2405.12979/) (2024)
- [Extreme Rotation Estimation using Dense Correlation Volumes](https://mlsanity.com/paper/2104.13530/) (2021)
- [Doppelgangers: Learning to Disambiguate Images of Similar Structures](https://mlsanity.com/paper/2309.02420/) (2023)
- [Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction](https://mlsanity.com/paper/2604.08542/) (2026)
- [ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training](https://mlsanity.com/paper/2603.04385/) (2026)
- [Doppelgangers++: Improved Visual Disambiguation with Geometric 3D Features](https://mlsanity.com/paper/2412.05826/) (2024)
- [LFM-3D: Learnable Feature Matching Across Wide Baselines Using 3D Signals](https://mlsanity.com/paper/2303.12779/) (2023)
- [Extreme Rotation Estimation in the Wild](https://mlsanity.com/paper/2411.07096/) (2024)

## Built on by (most cited first, 4 of 4)

- [SceneAligner: 3D-Grounded Floorplan Localization in the Wild](https://mlsanity.com/paper/2605.22581/) (2026)
- [Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth](https://mlsanity.com/paper/2605.19797/) (2026)
- [Honey, I Shrunk the Arc de Triomphe!](https://mlsanity.com/paper/2606.02379/) (2026)
- [RoMa-Omega: What Feed-Forward 3D Models Know About Image Matching](https://mlsanity.com/paper/2609.09507/) (2026)

## Abstract (arXiv)

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.