Newest papers

MVLoMa: Multi-View Local Feature Matching with Any Geometry Foundation Model

Xinyang Lu, Shengzhe Wei, Sheng Tang, Weiqi Zhang, Juntong Fang, Zesong Li · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31321 · cited by 0 works (OpenAlex) · open-access PDF

Hindi

Local feature matching is typically formulated for image pairs, although structure-from-motion and visual localization commonly match one reference image against many retrieved or cvisible neighbors. Applying a pairwise matching independently to these center-neighbour edges duplicates reference-side calculation and prevents the matcher from jointly describing all images on a star, then injects the resulting cross-view geometric context into local descriptors. To address these limitations, we introduce MVLoMa, a sparse star-graph matcher that extends LoMa from image pairs to multiple views. MVLoMa first uses a frozen multi-view geometry model to jointly describe all images on a star, then injects the resulting cross-view geometric context into local descriptors. It then mat

Machine translation (Meta M2M100); the English original follows.

Abstract

Local feature matching is typically formulated for image pairs, although structure-from-motion and visual localization commonly match one reference image against many retrieved or covisible neighbours. Applying a pairwise matcher independently to these centre-neighbour edges duplicates reference-side computation and prevents the matcher from exploiting complementary multi-view geometric evidence from the remaining observations. To address these limitations, we introduce MVLoMa, a sparse star-graph matcher that extends LoMa from image pairs to multiple views. MVLoMa first uses a frozen multi-view geometry model to jointly describe all images in a star, then injects the resulting cross-view geometric context into local descriptors. It then matches the centre image to all neighbours in a single forward pass through per-view self-attention and bidirectional centre-neighbour cross-attention. For supervision, we derive positive correspondences only from depth-valid, mutually visible dense warps and explicitly penalize high-confidence matches that violate epipolar geometry. On 25-view star graphs from HyperSim, ScanNet++, Mip-NeRF 360, and Tanks and Temples, MVLoMa obtains the best macro-average relative-pose AUC among the compared methods at all three thresholds (58.65/85.41/90.99). Its matcher is 2.20 times faster than sequential evaluation of the 24 centre-neighbour edges. The same design supports four tested frozen geometry encoders -- DA3, $π^3$, VGGT, and VGGT-$Ω$ -- with DA3-Giant performing best on all reported encoder-ablation metrics. Controlled ablations further isolate the effects of geometry-aware descriptors, visibility filtering, geometric negative supervision, and joint multi-view inference.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Epipolar geometry, Artificial intelligence, Computer vision, Matching (statistics), Feature (linguistics), Context (archaeology)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange