# An Evaluation of DUSt3R/MASt3R/VGGT 3D Reconstruction on Photogrammetric Aerial Blocks

arXiv: https://arxiv.org/abs/2507.14798 · HTML: https://mlsanity.com/paper/2507.14798/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 87 references that are in the map.
- First posted on arXiv 20 Jul 2025.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [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)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction](https://mlsanity.com/paper/2109.00512/) (2021)
- [Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass](https://mlsanity.com/paper/2501.13928/) (2025)
- [SynSin: End-to-end View Synthesis from a Single Image](https://mlsanity.com/paper/1912.08804/) (2019)
- [Learning to Recover 3D Scene Shape from a Single Image](https://mlsanity.com/paper/2012.09365/) (2020)
- [Stereo Magnification: Learning View Synthesis using Multiplane Images](https://mlsanity.com/paper/1805.09817/) (2018)
- [DeMoN: Depth and Motion Network for Learning Monocular Stereo](https://mlsanity.com/paper/1612.02401/) (2016)
- [ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals](https://mlsanity.com/paper/1905.02082/) (2019)
- [Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction](https://mlsanity.com/paper/1803.03893/) (2018)
- [Map-free Visual Relocalization: Metric Pose Relative to a Single Image](https://mlsanity.com/paper/2210.05494/) (2022)
- [Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networks](https://mlsanity.com/paper/1909.00321/) (2019)
- [Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era](https://mlsanity.com/paper/1906.06543/) (2019)
- [AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis](https://mlsanity.com/paper/2504.13157/) (2025)
- [Learned Multi-Patch Similarity](https://mlsanity.com/paper/1703.08836/) (2017)
- [Self-supervised monocular depth estimation from oblique UAV videos](https://mlsanity.com/paper/2012.10704/) (2020)
- [Image Fusion in Remote Sensing: An Overview and Meta Analysis](https://mlsanity.com/paper/2401.08837/) (2024)
- [Point Cloud Registration for LiDAR and Photogrammetric Data: a Critical Synthesis and Performance Analysis on Classic and Deep Learning Algorithms](https://mlsanity.com/paper/2302.07184/) (2023)
- [A Comparative Study on Deep-Learning Methods for Dense Image Matching of Multi-angle and Multi-date Remote Sensing Stereo Images](https://mlsanity.com/paper/2210.14031/) (2022)
- [Self-Supervised Learning for Stereo Reconstruction on Aerial Images](https://mlsanity.com/paper/1907.12446/) (2019)

## Built on by (most cited first, 5 of 5)

- [OccuFly: A 3D Vision Benchmark for Semantic Scene Completion from the Aerial Perspective](https://mlsanity.com/paper/2512.20770/) (2025)
- [Uncertainty Quality of VGGT: An Analysis on the DTU Benchmark Dataset](https://mlsanity.com/paper/2606.16479/) (2026)
- [Geometric Consistency Protocol for Foundation Model Features in Multi-View Satellite Imagery](https://mlsanity.com/paper/2606.17564/) (2026)
- [EO-VGGT: Orbital Ray-Conditioned 3D Foundation Models for Satellite Multi-View Reconstruction](https://mlsanity.com/paper/2607.00417/) (2026)
- [A Comparison of Multi-View Stereo Methods for Photogrammetric 3D Reconstruction: From Traditional to Learning-Based Approaches](https://mlsanity.com/paper/2604.10246/) (2026)

## Abstract (arXiv)

State-of-the-art 3D computer vision algorithms continue to advance in handling sparse, unordered image sets. Recently developed foundational models for 3D reconstruction, such as Dense and Unconstrained Stereo 3D Reconstruction (DUSt3R), Matching and Stereo 3D Reconstruction (MASt3R), and Visual Geometry Grounded Transformer (VGGT), have attracted attention due to their ability to handle very sparse image overlaps. Evaluating DUSt3R/MASt3R/VGGT on typical aerial images matters, as these models may handle extremely low image overlaps, stereo occlusions, and textureless regions. For redundant collections, they can accelerate 3D reconstruction by using extremely sparsified image sets. Despite tests on various computer vision benchmarks, their potential on photogrammetric aerial blocks remains unexplored. This paper conducts a comprehensive evaluation of the pre-trained DUSt3R/MASt3R/VGGT models on the aerial blocks of the UseGeo dataset for pose estimation and dense 3D reconstruction. Results show these methods can accurately reconstruct dense point clouds from very sparse image sets (fewer than 10 images, up to 518 pixels resolution), with completeness gains up to +50% over COLMAP. VGGT also demonstrates higher computational efficiency, scalability, and more reliable camera pose estimation. However, all exhibit limitations with high-resolution images and large sets, as pose reliability declines with more images and geometric complexity. These findings suggest transformer-based methods cannot fully replace traditional SfM and MVS, but offer promise as complementary approaches, especially in challenging, low-resolution, and sparse scenarios.