Deep Learning Reforms Image Matching: A Survey and Outlook

• URL: http://arxiv.org/abs/2506.04619v1
• Date: Thu, 05 Jun 2025 04:25:22 GMT
• Title: Deep Learning Reforms Image Matching: A Survey and Outlook
• Authors: Shihua Zhang, Zizhuo Li, Kaining Zhang, Yifan Lu, Yuxin Deng, Linfeng Tang, Xingyu Jiang, Jiayi Ma,
• Abstract summary: Image matching serves as a cornerstone in computer vision and underpins a wide range of applications.<n>Recent deep learning advances have significantly boosted both robustness and accuracy.<n>This survey adopts a unique perspective by comprehensively reviewing how deep learning has incrementally transformed the classical image matching pipeline.
• Score: 38.104899835728574
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image matching, which establishes correspondences between two-view images to recover 3D structure and camera geometry, serves as a cornerstone in computer vision and underpins a wide range of applications, including visual localization, 3D reconstruction, and simultaneous localization and mapping (SLAM). Traditional pipelines composed of ``detector-descriptor, feature matcher, outlier filter, and geometric estimator'' falter in challenging scenarios. Recent deep-learning advances have significantly boosted both robustness and accuracy. This survey adopts a unique perspective by comprehensively reviewing how deep learning has incrementally transformed the classical image matching pipeline. Our taxonomy highly aligns with the traditional pipeline in two key aspects: i) the replacement of individual steps in the traditional pipeline with learnable alternatives, including learnable detector-descriptor, outlier filter, and geometric estimator; and ii) the merging of multiple steps into end-to-end learnable modules, encompassing middle-end sparse matcher, end-to-end semi-dense/dense matcher, and pose regressor. We first examine the design principles, advantages, and limitations of both aspects, and then benchmark representative methods on relative pose recovery, homography estimation, and visual localization tasks. Finally, we discuss open challenges and outline promising directions for future research. By systematically categorizing and evaluating deep learning-driven strategies, this survey offers a clear overview of the evolving image matching landscape and highlights key avenues for further innovation.

Related papers

• Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation [62.87088388345378]
  We introduce a diffusion-based framework that performs aligned novel view image and geometry generation via a warping-and-inpainting methodology.<n>Method leverages off-the-shelf geometry predictors to predict partial geometries viewed from reference images.<n>Cross-modal attention distillation is proposed to ensure accurate alignment between generated images and geometry.
  arXiv  Detail & Related papers  (2025-06-13T16:19:00Z)
• Multi-view dense image matching with similarity learning and geometry priors [0.0]
  MV-DeepSimNets is a suite of deep neural networks designed for multi-view similarity learning.<n>Our approach incorporates an online geometry prior to characterize pixel relationships.<n>Our method geometric preconditioning effectively adapts epipolar-based features for enhanced multi-view reconstruction.
  arXiv  Detail & Related papers  (2025-05-16T13:55:40Z)
• Image Matching Filtering and Refinement by Planes and Beyond [8.184339776177486]
  This paper introduces a modular, non-deep learning method for filtering and refining sparse correspondences in image matching.<n>The proposed method is extensively evaluated on standard datasets and image matching pipelines, and compared with state-of-the-art approaches.<n> Experimental results demonstrate that our proposed non-deep learning, geometry-based approach achieves performances that are either superior to or on par with recent state-of-the-art deep learning methods.
  arXiv  Detail & Related papers  (2024-11-14T14:37:50Z)
• Mismatched: Evaluating the Limits of Image Matching Approaches and Benchmarks [9.388897214344572]
  Three-dimensional (3D) reconstruction from two-dimensional images is an active research field in computer vision. Traditionally, parametric techniques have been employed for this task. Recent advancements have seen a shift towards learning-based methods.
  arXiv  Detail & Related papers  (2024-08-29T11:16:34Z)
• Geometric-aware Pretraining for Vision-centric 3D Object Detection [77.7979088689944]
  We propose a novel geometric-aware pretraining framework called GAPretrain. GAPretrain serves as a plug-and-play solution that can be flexibly applied to multiple state-of-the-art detectors. We achieve 46.2 mAP and 55.5 NDS on the nuScenes val set using the BEVFormer method, with a gain of 2.7 and 2.1 points, respectively.
  arXiv  Detail & Related papers  (2023-04-06T14:33:05Z)
• Fusing Local Similarities for Retrieval-based 3D Orientation Estimation of Unseen Objects [70.49392581592089]
  We tackle the task of estimating the 3D orientation of previously-unseen objects from monocular images. We follow a retrieval-based strategy and prevent the network from learning object-specific features. Our experiments on the LineMOD, LineMOD-Occluded, and T-LESS datasets show that our method yields a significantly better generalization to unseen objects than previous works.
  arXiv  Detail & Related papers  (2022-03-16T08:53:00Z)
• VolumeFusion: Deep Depth Fusion for 3D Scene Reconstruction [71.83308989022635]
  In this paper, we advocate that replicating the traditional two stages framework with deep neural networks improves both the interpretability and the accuracy of the results. Our network operates in two steps: 1) the local computation of the local depth maps with a deep MVS technique, and, 2) the depth maps and images' features fusion to build a single TSDF volume. In order to improve the matching performance between images acquired from very different viewpoints, we introduce a rotation-invariant 3D convolution kernel called PosedConv.
  arXiv  Detail & Related papers  (2021-08-19T11:33:58Z)
• Deep Two-View Structure-from-Motion Revisited [83.93809929963969]
  Two-view structure-from-motion (SfM) is the cornerstone of 3D reconstruction and visual SLAM. We propose to revisit the problem of deep two-view SfM by leveraging the well-posedness of the classic pipeline. Our method consists of 1) an optical flow estimation network that predicts dense correspondences between two frames; 2) a normalized pose estimation module that computes relative camera poses from the 2D optical flow correspondences, and 3) a scale-invariant depth estimation network that leverages epipolar geometry to reduce the search space, refine the dense correspondences, and estimate relative depth maps.
  arXiv  Detail & Related papers  (2021-04-01T15:31:20Z)
• Early Bird: Loop Closures from Opposing Viewpoints for Perceptually-Aliased Indoor Environments [35.663671249819124]
  We present novel research that simultaneously addresses viewpoint change and perceptual aliasing. We show that our integration of VPR with SLAM significantly boosts the performance of VPR, feature correspondence, and pose graph submodules. For the first time, we demonstrate a localization system capable of state-of-the-art performance despite perceptual aliasing and extreme 180-degree-rotated viewpoint change.
  arXiv  Detail & Related papers  (2020-10-03T20:18:55Z)
• Towards Better Generalization: Joint Depth-Pose Learning without PoseNet [36.414471128890284]
  We tackle the essential problem of scale inconsistency for self-supervised joint depth-pose learning. Most existing methods assume that a consistent scale of depth and pose can be learned across all input samples. We propose a novel system that explicitly disentangles scale from the network estimation.
  arXiv  Detail & Related papers  (2020-04-03T00:28:09Z)

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.