Cross-Modal Feature Matching

Ask about this topic

Overview

Cross-modal feature matching identifies which regions, points, or tokens in different modalities refer to the same scene element, enabling tasks such as image registration, 2D–3D alignment, retrieval, and sensor localization. Methods commonly learn shared or modality-adapted features using contrastive alignment, cross-attention, transformers, or pretrained vision models, then refine correspondences with geometric constraints, outlier rejection, and coarse-to-fine search. Evaluation spans settings such as RGB–infrared and optical–SAR registration, image-to-point-cloud matching on RGB-D Scenes and 7-Scenes, and camera–LiDAR localization on KITTI. A central challenge is balancing semantic similarity with geometrically valid matches while maintaining robustness across sensor shifts, domains, and deployment constraints.

Latest papers

CardsList

66 papers7 papers in the last four weeks, down 30% on the four weeks before. 0.0% of all new papers.

  1. FlexiMIND: Combined Pretrained Vision Features and Local Structure for Training-Free Deformable Medical Image Registration

    Oct 25, 2026Mojtaba Safari, Mingzhe Hu, Shansong Wang +6Medical Image RegistrationDeformable Image Registration

    Department of Radiation and Cellular Oncology, The University of Chicago, Chicago, IL, United States. · Department of Computer Science and Informatics, Emory University, Atlanta, GA, United States. · Department of Radiology, The University of Chicago, Chicago, IL, United States.

  2. RankAlign: Vision-Language Representation Alignment via Rank Transformation

    Oct 22, 2026Enzhe Zhao, Marco Fiorucci, Lamberto BallanVision-Language AlignmentCross-Modal Feature Matching

    University of Padova, Italy · Harbin Institute of Technology, China

  3. Flow-CLIP: Image-Conditioned Residual Scoring for CompositionalImage-Text Matching

    Oct 15, 2026Minghong Wei, Enguang Zhu, Pu Cao +2Vision-Language AlignmentCross-Modal Feature Matching

    School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications, Beijing, 100082, China

  4. TartanMatch: Towards Universal Dense Correspondence Across Modalities

    Oct 10, 2026Hyeokjoon Kwon, Jiting Cai, Ruogu Li +7Cross-Modal Feature MatchingUnified Multimodal Models

    The authors are with the Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA · Kritan Bhandari is with Fisk University, Nashville, TN, USA

  5. Structure-Aware Matching for Robust UAV Thermal-to-Satellite Geo-Localization

    Oct 9, 2026Chun Liu, Yuxin Wang, Zhenxiang Huo +3Cross-View Geo-LocalizationCross-Modal Feature Matching

    State Key Laboratory of Spatial Datum, Henan University, Zhengzhou 450046, China · College of Remote Sensing and Geoinformatics Engineering, Henan University, Zhengzhou 450046, China · School of Computer and Information Engineering, Henan University, Zhengzhou 450046, China +1

  6. Geometry-Aligned Semantic Matching for Cross-Modal Planar Image Registration

    Oct 2, 2026Zhiwei Wang, Defeng He, Yuxing Li +2Image MatchingCross-Modal Image Registration

  7. ARCH-B: Architectural Representation, Comprehension and Hierarchy Benchmark

    Sep 28, 2026Kieran Sagar Parikh, Jose Luis Garcia del Castillo y LopezSemantic CorrespondenceCross-Modal Alignment

    Harvard University · Northeastern University

  8. UNMATCH: Selective Unbalanced Token-Patch Matching for Forensic Image-Claim Verification

    Sep 24, 2026Xinjin Li, Lian Lian, Yuanzhe Yang +6Claim VerificationDigital Image Forensics

    Columbia University New York, United States · Rice University Houston, United States

  9. GRIP: Gaussian Rendering as a Cross-Modal Bridge for Image-to-Point Cloud Registration

    Sep 22, 2026Karim Slimani, Catherine Achard, Eric Marchand +12D-3D Image RegistrationPoint Cloud Registration

    ISIR, Sorbonne Univ., CNRS, INSERM, Paris, France · Univ Rennes, Inria, CNRS, Irisa, Rennes, France

  10. MatcherCompass: A Deployment-Aware Benchmark to Guide Image Matcher Selection in the Wild

    Sep 22, 2026Hyunwoo Kim, Giseop KimImage MatchingCross-Modal Feature Matching

    Department of Robotics and Mechatronics Engineering, DGIST, Daegu, Republic of Korea

  11. Mask 2D-3D: Adaptive Dual-Masked Autoencoder Network for Image-to-Point Cloud Registration

    Sep 16, 2026Zhixin Cheng, Jiacheng Deng, Xiaotian Yin +3Masked AutoencodersPoint Cloud Registration

    School of Computer Science and Technology, Hefei University of Technology, Hefei 230601, China · School of Information Science and Technology, University of Science and Technology of China, Hefei 230027, China · Institute of Advanced Technology, University of Science and Technology of China, Hefei 230027, China

  12. Multimodal Floorplan Encoding: Learning Dense Modality-Invariant Representations

    Sep 11, 2026Xavier Anadón, Rémi Pautrat, Rui WangLatent Space AlignmentCross-Modal Representation Learning

    University of Zaragoza, Spain · Microsoft, Switzerland

  13. Beyond Ambiguous Visual Cues: Studying Physiological Disruptions and Cross-Modal Inconsistencies in Deepfake Videos

    Sep 11, 2026Chenxi Yang, Yassine Ouzar, Larbi BoubchirRemote PhotoplethysmographyDeepfake Detection

    LIASD Laboratory Shanghai Jiaotong University Shanghai, China · LIASD Laboratory University of Paris 8 Saint-Denis, France

  14. RoMa-ΩΩ: What Feed-Forward 3D Models Know About Image Matching

    Sep 8, 2026David Nordström, Xinyue Zhang, Thibaut Loiseau +2Image Matching3D Representation Learning

    Chalmers University of Technology, Sweden · Mobile Perception Lab, ShanghaiTech University, China · LIGM, Ecole des Ponts, Univ. Gustave Eiffel, CNRS, France

  15. DXPR: Depth-Based Vision-LiDAR Cross-Modal Place Recognition Using Vision Foundation Models

    Sep 8, 2026Yungsoo Han, Youngseok Jang, Seungwon Roh +2LiDAR Place RecognitionVisual Place Recognition

    Department of Aerospace Engineering, Seoul National University, Seoul, Republic of Korea. · InnoCORE AI-Transformed Aerospace Research Center, KAIST, Daejeon, Republic of Korea. · Interdisciplinary Program in Artificial Intelligence, Seoul National University, Seoul, Republic of Korea.

  16. Radiation, Rotation and Scale Invariant Feature Descriptor for Multimodal Image Matching

    Sep 6, 2026Yuanxin Ye, Tengfeng Tang, Tao Peng +3Cross-Modal Feature MatchingInvariant Representation Learning

    Faculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu, China · School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China · State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing,Wuhan University, Wuhan, China

  17. CrossFeat: Bridging Imaging Modalities in Feature Descriptor Space

    Aug 31, 2026Paul Schneider, Nazim HaouchineCross-Modal Representation LearningMultimodal Disentangled Representation Learning

    Harvard Medical School, Brigham and Women’s Hospital, Boston, MA, USA · Technical University of Munich, Munich, Germany

  18. Cross-Spectral Dense Correspondence for Multimodal Spectral Medical Imaging

    Aug 28, 2026Eric L. Wisotzky, Jost Triller, Simon W. Härtl +3Image MatchingCross-Modal Feature Matching

    Vision & Imaging Technologies, Fraunhofer Heinrich Hertz Institute HHI, Berlin, Germany · Visual Computing, Humboldt University Berlin, Germany · Functional Imaging in Surgical Oncology, National Center for Tumordiseases, Dresden, Germany

  19. MulVec: Fine-Grained Role-Aware Matching for Training-Free Zero-Shot Composed Image Retrieval

    Aug 26, 2026Zihao Zhang, Dayan Wu, Xinze Liu +6Composed Image RetrievalFine-Grained Image Retrieval

    Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China · Department of Applied Mathematics and Statistics, Johns Hopkins University, Baltimore, MD 21218, USA

  20. Action-Aligned Retrieval with Pairwise Multimodal Reranking for Text-Based Person Anomaly Search

    Aug 24, 2026Thanh-Khoi Nguyen, Thanh-Nhan Vo, Trong-Thuan Nguyen +1Anomaly DetectionCross-Modal Feature Matching

    University of Science, VNU-HCM, Vietnam · Vietnam National University, Ho Chi Minh City, Vietnam

  21. DMM-Align: Closed-Loop Optimization for 2D-3D Registration with Dual-Role Diffusion

    Aug 17, 2026Chongjian Wang, Junjie Gao2D-3D Image RegistrationCross-Modal Image Registration

    Shandong Women’s University Jinan, China · Shandong University of Science and Technology Qingdao, China

  22. TeaMatch: Teachable Cross-Modal Representation Learning for 2D-3D Matching

    Aug 10, 2026Chongjian Wang, Junjie GaoCross-Modal Representation LearningImage Matching

    Shandong Women’s University · Jinan, China · Shandong University of Science and Technology +1

  23. SLAP: Selective Local Vision-Language Alignment for Fish Re-Identification via Partial Optimal Transport

    Aug 9, 2026Cigdem Beyan, Tonje Knutsen Sordalen, Kim Tallaksen HalvorsenInverse Optimal TransportAnimal Re-Identification

    Department of Computer Science, University of Verona, 37134 Verona, Italy · Institute of Marine Research, Nye Flødevigveien 20, 4817 His, Norway · University of Agder, Centre for Coastal Research, 4604 Grimstad, Norway

  24. Face and Voice Cross-modal Association with Learning Convex Feature Embedding

    Jul 30, 2026Taewan Kim, Jiwoo KangCross-Modal Feature Matching

    1Data Science Major, Dongduk Women’s University, Seoul, 02748, South Korea. · 2*Division of Artificial Intelligence Engineering, Sookmyung Women’s University, Seoul, 04310, South Korea.

  25. XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection

    Jul 26, 2026Mingxiu Cai, Zhe Zhang, Gaochang Wu +1Industrial Anomaly DetectionAnomaly Localization

    State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China

  26. Cross-Coordinate Correspondence Pruning for Image-to-Point Cloud Registration

    Jul 19, 2026Xin Liu, Rong Qin, Huipeng Lin +5Point Cloud RegistrationCross-Modal Feature Matching

    VCIP & TMCC & DISSec, College of Computer Science, Nankai University, Tianjin, China. · AutoCity (Shenzhen) Autonomous Driving Co., Ltd, Shenzhen, China. · School of Intelligent Science and Technology, University of Science and Technology Beijing, Beijing, China. +4

  27. SUFLECA: Scaling Up Feature Learning for CAD-to-image Alignment

    Jul 16, 2026Saad Ejaz, Miguel Fernandez-Cortizas, Javier Civera +2Object Pose EstimationGeometric Representation Learning

    Automation and Robotics Research Group, Interdisciplinary Centre for Security, Reliability, and Trust (SnT), University of Luxembourg, Luxembourg · I3A, Universidad de Zaragoza

  28. Label-Free Target-Domain Adaptation for Unconstrained Event-Image Feature Matching via Dual-Stage Distillation

    Jul 11, 2026Zhonghua Yi, Hao Shi, Qi Jiang +3Event-Based VisionCross-Modal Knowledge Distillation

    Zhejiang University · Ant Group · National University of Defense Technology +1

  29. PLGSA-Transformer: Periocular Landmark-Guided Attention with Occlusion-Adaptive Cosine Thresholding for Cross-Modal Masked and Unmasked Face Recognition

    Jul 3, 2026Dana A AbdullahCross-Modal Feature MatchingFace Recognition

    Faculty of Engineering and Computer Science, Qaiwan International University, Sulaymaniyah, KRG, Iraq. · Department of Information and Communication Technology Center (ICTC)-System Information, Ministry of Higher Education and Scientific Research.

  30. DetailAnywhere: Fashion Detail Generation via Cross-Modal Feature Alignment Distillation

    Jul 2, 2026Zijun Li, Yimin Zhou, Jia Sun +12Diffusion Model DistillationConditional Image Generation

    Kuaishou Technology · AIM for Health Lab, Monash University