Grounding Image Matching in 3D with MASt3R

By Vincent Leroy, Yohann Cabon, Jérôme Revaud. European Conference on Computer Vision, 2024

1,001 citations recorded by the source corpus.

Image Matching is a core component of all best-performing algorithms and pipelines in 3D vision. Yet despite matching being fundamentally a 3D problem, intrinsically linked to camera pose and scene geometry, it is typically treated as a 2D problem. This makes sense as the goal of matching is to establish correspondences between 2D pixel fields, but also seems like a potentially hazardous choice. In this work, we take a different stance and propose to cast matching as a 3D task with DUSt3R, a recent and powerful 3D reconstruction framework based on Transformers. Based on pointmaps regression, this method displayed impressive robustness in matching views with extreme viewpoint changes, yet with limited accuracy. We aim here to improve the matching capabilities of such an approach while preserving its robustness. We thus propose to augment the DUSt3R network with a new head that outputs dense local features, trained with an additional matching loss. We further address the issue of quadratic complexity of dense matching, which becomes prohibitively slow for downstream applications if not carefully treated. We introduce a fast reciprocal matching scheme that not only accelerates matching by orders of magnitude, but also comes with theoretical guarantees and, lastly, yields improved results. Extensive experiments show that our approach, coined MASt3R, significantly outperforms the state of the art on multiple matching tasks. In particular, it beats the best published methods by 30% (absolute improvement) in VCRE AUC on the extremely challenging Map-free localization dataset.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/4f997c404e97087194d2df538deb82b2c5428c1e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Ying Shan
2. Jinbo Xing
3. Xiaoyu Li
4. Wangbo Yu
5. Li Yuan
6. Xiangjun Gao
7. Wenbo Hu
8. Tien-Tsin Wong

Citations in the corpus

• Depth Anything 3: Recovering the Visual Space from Any Views (2025, neutral): “Follow-up models extended this paradigm with multi-view inputs [10, 85, 94, 110], video input [19, 59, 94, 121], robust correspondence modeling [48], camera parameter injection [39, 43], large-scale SfM [18], SLAM applications [54], and view synthesis with 3D Gaussians [11, 13, 41, 79, 108, 122].”
• VGGT: Visual Geometry Grounded Transformer (2025, neutral): “MASt3R [43] have shown promising results in this direction, but these networks can only process two images at once and rely on post-processing to reconstruct more images, fusing pairwise reconstructions.”
• Continuous 3D Perception Model with Persistent State (2025, neutral): “Our primary set of baselines are DUSt3R [86], MASt3R [40], Spann3R [81], and MonST3R [98], where the latter two are concurrent works.”
• Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass (2025, neutral): “For example, [14, 19, 25, 42, 51, 68] improve feature extraction and correspondences, [27, 50, 59, 71] learn to estimate camera pose, and [52] introduce a bundle adjustment layer.”
• ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis (2024, background): “On the other hand, recent dense stereo methods [19], [20] have made fast point cloud reconstruction from single or sparse images accessible.”