LoMa: Local Feature Matching Revisited

• URL: http://arxiv.org/abs/2604.04931v1
• Date: Mon, 06 Apr 2026 17:59:49 GMT
• Title: LoMa: Local Feature Matching Revisited
• Abstract summary: Local feature matching has long been a fundamental component of 3D vision systems such as Structure-from-Motion (SfM)<n>In this paper, we revisit local feature matching from a data-driven perspective.<n>We combine large and diverse data mixtures, modern training recipes, scaled model capacity, and scaled compute, resulting in remarkable gains in performance.
• Score: 56.73318466794448
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Local feature matching has long been a fundamental component of 3D vision systems such as Structure-from-Motion (SfM), yet progress has lagged behind the rapid advances of modern data-driven approaches. The newer approaches, such as feed-forward reconstruction models, have benefited extensively from scaling dataset sizes, whereas local feature matching models are still only trained on a few mid-sized datasets. In this paper, we revisit local feature matching from a data-driven perspective. In our approach, which we call LoMa, we combine large and diverse data mixtures, modern training recipes, scaled model capacity, and scaled compute, resulting in remarkable gains in performance. Since current standard benchmarks mainly rely on collecting sparse views from successful 3D reconstructions, the evaluation of progress in feature matching has been limited to relatively easy image pairs. To address the resulting saturation of benchmarks, we collect 1000 highly challenging image pairs from internet data into a new dataset called HardMatch. Ground truth correspondences for HardMatch are obtained via manual annotation by the authors. In our extensive benchmarking suite, we find that LoMa makes outstanding progress across the board, outperforming the state-of-the-art method ALIKED+LightGlue by +18.6 mAA on HardMatch, +29.5 mAA on WxBS, +21.4 (1m, 10$^\circ$) on InLoc, +24.2 AUC on RUBIK, and +12.4 mAA on IMC 2022. We release our code and models publicly at https://github.com/davnords/LoMa.

Related papers

• An Embarrassingly Simple Graph Heuristic Reveals Shortcut-Solvable Benchmarks for Sequential Recommendation [50.09718257952108]
  Sequentialsolv has increasingly shifted toward generative recommenders that combine sequential patterns with semantic item information.<n>These methods are often evaluated on a small set of widely used benchmarks, raising a key question: do these benchmarks actually require the advanced modeling capabilities that modern generative recommenders claim to provide?<n>We conduct a benchmark audit with an intentionally simple graph. Starting from only the last one or two items, it retrieves candidates from a few-hop item-transition graph and ranks them by item-feature similarity.
  arXiv  Detail & Related papers  (2026-05-08T02:00:11Z)
• RoMa v2: Harder Better Faster Denser Feature Matching [56.71494120301684]
  Dense feature matching aims to estimate all correspondences between two images of a 3D scene.<n>Existing dense matchers fail or perform poorly for many hard real-world scenarios.<n>In this paper, we attack these weaknesses on a wide front through a series of systematic improvements.
  arXiv  Detail & Related papers  (2025-11-19T18:59:38Z)
• Cluster and Predict Latent Patches for Improved Masked Image Modeling [25.616762947410045]
  We introduce CAPI, a novel pure-MIM framework that relies on the prediction of latent clusterings.<n>Our approach leverages a clustering-based loss, which is stable to train, and exhibits promising scaling properties.<n>Our ViT-L backbone, CAPI, achieves 83.8% accuracy on ImageNet and 32.1% mIoU on ADE20K with simple linear probes.
  arXiv  Detail & Related papers  (2025-02-12T20:17:10Z)
• Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba [48.45301469664908]
  3D Hand reconstruction from a single RGB image is challenging due to articulated motion, self-occlusion, and interaction with objects.<n>Existing SOTA methods employ attention-based transformers to learn the 3D hand pose and shape.<n>We propose a novel graph-guided Mamba framework, named Hamba, which bridges graph learning and state space modeling.
  arXiv  Detail & Related papers  (2024-07-12T19:04:58Z)
• RoMa: Robust Dense Feature Matching [17.015362716393216]
  Feature matching is an important computer vision task that involves estimating correspondences between two images of a 3D scene. We propose a model, leveraging frozen pretrained features from the foundation model DINOv2. To further improve robustness, we propose a tailored transformer match decoder.
  arXiv  Detail & Related papers  (2023-05-24T17:59:04Z)
• Learning from Temporal Spatial Cubism for Cross-Dataset Skeleton-based Action Recognition [88.34182299496074]
  Action labels are only available on a source dataset, but unavailable on a target dataset in the training stage. We utilize a self-supervision scheme to reduce the domain shift between two skeleton-based action datasets. By segmenting and permuting temporal segments or human body parts, we design two self-supervised learning classification tasks.
  arXiv  Detail & Related papers  (2022-07-17T07:05:39Z)
• Modality-Aware Triplet Hard Mining for Zero-shot Sketch-Based Image Retrieval [51.42470171051007]
  This paper tackles the Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) problem from the viewpoint of cross-modality metric learning. By combining two fundamental learning approaches in DML, e.g., classification training and pairwise training, we set up a strong baseline for ZS-SBIR. We show that Modality-Aware Triplet Hard Mining (MATHM) enhances the baseline with three types of pairwise learning.
  arXiv  Detail & Related papers  (2021-12-15T08:36:44Z)
• MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image [18.68544438724187]
  We propose a framework for single-view hand mesh reconstruction, which can simultaneously achieve high reconstruction accuracy, fast inference speed, and temporal coherence. Our framework, called MobRecon, comprises affordable computational costs and miniature model size, which reaches a high inference speed of 83FPS on Apple A14 CPU.
  arXiv  Detail & Related papers  (2021-12-06T03:01:24Z)
• MVHM: A Large-Scale Multi-View Hand Mesh Benchmark for Accurate 3D Hand Pose Estimation [32.12879364117658]
  Estimating 3D hand poses from a single RGB image is challenging because depth ambiguity leads the problem ill-posed. We design a spin match algorithm that enables a rigid mesh model matching with any target mesh ground truth. We present a multi-view hand pose estimation approach to verify that training a hand pose estimator with our generated dataset greatly enhances the performance.
  arXiv  Detail & Related papers  (2020-12-06T07:55:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.