Harder Better Faster Denser Feature Matching

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, up 67% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 37

All topics

FAST: Flow Any Scene Transformer
Sep 30, 2026Yongjian Zhang, Longguang Wang, Zhuo Song +3Harder Better Faster Denser Feature Matching Recent Vision Foundation Models
School of Electronics and Communication Engineering, the Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University, Shenzhen, China · Hong Kong Polytechnic University, HKSAR, China · School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China
UltraMatch: Transport Path Routing for Ultra-Fast and Memory-Efficient Image Matching
Sep 29, 2026Jiajun Le, Yifan Lu, Zizhuo Li +3Harder Better Faster Denser Feature Matching Ultrafast
Electronic Information School, Wuhan University, China · Xiaomi Corporation, China · School of Computer Science and Technology, Harbin Institute of Technology, China +1
The Devil is in the Spectrum Bias: Spectrum-Balanced Feature Matching for Robust Representation Distillation
Sep 28, 2026Kuniaki Saito, Yoshitaka UshikuHarder Better Faster Denser Feature Matching Recent Vision Foundation Models
OMRON SINIC X Corporation
MatcherCompass: A Deployment-Aware Benchmark to Guide Image Matcher Selection in the Wild
Sep 22, 2026Hyunwoo Kim, Giseop KimHarder Better Faster Denser Feature Matching Robotic Perception
Department of Robotics and Mechatronics Engineering, DGIST, Daegu, Republic of Korea
Long-Horizon Language Model Reinforcement Learning via Progressive Point Matching
Sep 7, 2026Preston Fu, Kevin Frans, Oleh Rybkin +2Large Language Model Reinforcement Learning Long-Horizon Task Planning
UC Berkeley · Carnegie Mellon University
POI-Loc: A Fine-Grained POI Localization Benchmark and an Asymmetric Global-to-Local Matching Method
Sep 2, 2026Lu Han, Xiting Sun, Hao Wang +4Visual Place Recognition Harder Better Faster Denser Feature Matching
Amap, Alibaba Group, Beijing, China
Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives
Aug 11, 2026Songlin Du, Xiaoyong Lu, Zeyu Wu +5Harder Better Faster Denser Feature Matching Cross-View
School of Automation, Southeast University, Nanjing 210096, China · School of Computer Science and Technology, Tongji University, Shanghai 201804, China · School of Intelligence Science and Technology and the Institute of Artificial Intelligence, University of Science and Technology Beijing, Beijing 100083, China +2
XFeat Revisited: Reproducibility and Evaluation of a Lightweight Image Matcher
Aug 10, 2026Lazar Đoković, Aimee LinHarder Better Faster Denser Feature Matching Capability-Speed Trade-Offs
Faculty of Computer and Information Science University of Ljubljana
KnifeHunter: Structured Local Representation Learning for Fine-Grained Knife Image Retrieval in Law Enforcement
Aug 7, 2026Syed Sameed Husain, Eng-Jon Ong, Stephen Simpson +3Digital Forensics Composed Image Retrieval
Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford GU27XH, UK · Metropolitan Police UK
SGFormer: Structure-Guided Transformer for Robust Local Feature Matching
Aug 4, 2026Runyu ZhuHarder Better Faster Denser Feature Matching Transformer Architectures
Double Down on Defense: Strengthening Deep Perceptual Hashes against Evasion Attacks without Retraining
Aug 4, 2026Bangjie Sun, Nayoung Kim, Mun Choon Chan +1Locality-Sensitive Hashing White-Box Spectral-Subspace-Guided Attack
National University of Singapore (NUS) · Korea Advanced Institute of Science and Technology (KAIST)
HOME: Robust Hough-space Matching Method for Structured and Textureless Videos
Jul 28, 2026Masaki SatohHarder Better Faster Denser Feature Matching Homography
Morpho, Inc. Tokyo, Japan
Adaptive Contrast Enhancement and Optimised Feature Matching for RootSIFT-Based Palm-Vein Recognition
Jul 17, 2026Kaveen Perera, Fouad Khelifi, Ammar BelatrecheAdaptive Histogram Equalization Harder Better Faster Denser Feature Matching
Computer & Information Sciences Department University of Northumbria at Newcastle, United Kingdom
GoStop: Reinforcement Learning for Adaptive Temporal Aggregation in Event-Based Feature Tracking
Jul 17, 2026Youngho Kim, Hoonhee Cho, Jae-Young Kang +1Motion Estimation Harder Better Faster Denser Feature Matching
KAIST
MGFace: Mask-Gated Face Matching via Conditional Similarity Routing
Jul 14, 2026Huy Che, Hoang-Minh Trinh, Dinh-Duy Phan +1Face Recognition Model One-Shot Medical Landmark Detection
University of Information Technology, Ho Chi Minh City, Vietnam · 2Vietnam National University, Ho Chi Minh City, Vietnam
Rank-1 Identity Consensus Predicts Gallery Enrollment in 1:N Face Matching More Accurately than Score Thresholding
Jul 14, 2026Gabriella Pangelinan, Aman Bhatta, Michael C. King +1Face Recognition Model Adaptive Thresholding
Florida Institute of Technology, Melbourne, FL · University of Notre Dame, Notre Dame, IN
Desc++: Efficient Descriptor Enhancement for Data Association in Existing Visual SLAM Systems
Jul 13, 2026Ting-Wei Ou, Huang-Ting Lin, Kuu-Young YoungOrb-Slam2 Simultaneous Localization And Mapping
Label-Free Target-Domain Adaptation for Unconstrained Event-Image Feature Matching via Dual-Stage Distillation
Jul 11, 2026Zhonghua Yi, Hao Shi, Qi Jiang +3Harder Better Faster Denser Feature Matching Cross-Modal Distillation
Zhejiang University · Ant Group · National University of Defense Technology +1
Confidence-feedback-weighted graph matching network: online-offline laser-induced damage site matching under complex interference
Jun 28, 2026Yueyue Han, Guanhua Chen, Hangcheng Dong +6Harder Better Faster Denser Feature Matching Query Image
School of Instrumentation Science and Engineering, Harbin Institute of Technology, Harbin 150001, China · Research Center of Laser Fusion, China Academy of Engineering Physics, Mianyang 621900, China
GRAFT: Graph-Based Affordance Transfer via Part Correspondence
Jun 23, 2026Mengying Lin, Utkarsh Mishra, Ajay Mandlekar +1Ground-Truth Correspondence Harder Better Faster Denser Feature Matching
Georgia Institute of Technology · NVIDIA
REDI-Match: Rotation-Equivariant Distillation for Efficient and Robust Dense Matching
Jun 23, 2026Yinji Ge, Guixu Zheng, Wulong Guo +5Harder Better Faster Denser Feature Matching Vision Foundation Models
1Tsinghua University · 2Southern University of Science and Technology · 3Beihang University +1
Topological summaries of fingerprint ridge patterns carry identity information
Jun 20, 2026Chad M. Topaz, Niny Arcila-Maya, Elizabeth Munch +2Fingerprint Topology
Williams College, Williamstown, MA 01267 · QSIDE Institute, Williamstown, MA 01267 · University of Colorado Boulder, Boulder, CO 80309 +3
Toward the Whole Picture: Accumulative Fingerprint Mapping and Reconstruction for Small-Area Mobile Sensors
Jun 14, 2026Xiongjun Guan, Jianjiang Feng, Jie ZhouFingerprint Biometrics
Department of Automation, Tsinghua University, Beijing 100084, China
SAMatcher: Co-Visibility Modeling with Segment Anything for Robust Feature Matching
Jun 2, 2026Xu Pan, Qiyuan Ma, Mingyue Dong +3Harder Better Faster Denser Feature Matching Segment Anything Model
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS), Wuhan University, Wuhan, P. R. China · National Key Laboratory of Space Target Awareness, Space Engineering University, Beijing, P. R. China
Multimodal Distribution Matching for Vision-Language Dataset Distillation
May 22, 2026Jongoh Jeong, Hoyong Kwon, Minseok Kim +1Cross-Modal Distillation Dataset Distillation
Visual Intelligence Lab., KAIST
PySIFT: GPU-Resident Deterministic SIFT for Deep Learning Vision Pipelines
May 18, 2026Sivakumar K. S., Mohammad Daniyalur Rahman, Gopi Raju MattaHarder Better Faster Denser Feature Matching Keypoint Detection
1Indian Institute of Technology Madras
Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers
May 16, 2026Shaodong Xu, Zhendong Wang, Litong Gong +4Diffusion Alignment Diffusion Transformers
University of Science and Technology of China
MicroscopyMatching: Towards a Ready-to-use Framework for Microscopy Image Analysis in Diverse Conditions
May 14, 2026Xiaofei Hui, Haoxuan Qu, Hossein Rahmani +3Microscopy Harder Better Faster Denser Feature Matching
School of Computing and Communications, Lancaster University, Lancaster, LA1 4WA, UK. · Department of Cell Biology, Harvard Medical School, Boston, MA 02115, USA. · Department of Molecular and Cellular Biology, Center for Brain Science, Harvard University, Cambridge, MA 02138, USA.
Preserve, Then Resolve: Many-to-Many Association and Robust Estimation with General-Purpose Visual Features
Apr 26, 2026Haodong Jiang, Mingzhe Li, Junfeng WuHarder Better Faster Denser Feature Matching Dino
School of Data Science, CUHK (SZ)
Region Matters: Efficient and Reliable Region-Aware Visual Place Recognition
Apr 24, 2026Shunpeng Chen, Yukun Song, Changwei Wang +6Visual Place Recognition Harder Better Faster Denser Feature Matching
School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China. · Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center, Qilu University of Technology. · Spatialtemporal AI. +1
Match-Any-Events: Zero-Shot Motion-Robust Feature Matching Across Wide Baselines for Event Cameras
Apr 20, 2026Ruijun Zhang, Hang Su, Kostas Daniilidis +1Harder Better Faster Denser Feature Matching Motion Estimation
Johns Hopkins University, Baltimore MD 21218, USA · ShanghaiTech University, Shanghai, China · University of Pennsylvania, Philadelphia PA 19104, USA +1
Learned Nonlocal Feature Matching and Filtering for RAW Image Denoising
Apr 19, 2026Marco Sánchez-Beeckman, Antoni BuadesIterative Denoising Methods Harder Better Faster Denser Feature Matching
IAC3 & Departament de Ciències Matemàtiques i Informàtica, Universitat de les Illes Balears · aDept. of Mathematics and Computer Science, Universitat de les Illes Balears, Cra. de Valldemossa km 7.5, Palma, 07122, Illes Balears, Spain · bInstitute of Applied Computing and Community Code (IAC3), Universitat de les Illes Balears, C/ Blaise Pascal 7, Parc BIT, Palma, 07121, Illes Balears, Spain
AsymLoc: Towards Asymmetric Feature Matching for Efficient Visual Localization
Apr 10, 2026Mohammad Omama, Gabriele Berton, Eric Foxlin +1Sequential Visual Localization Harder Better Faster Denser Feature Matching
The University of Texas at Austin · Work done as a part of a summer internship at Amazon. · Amazon
LoMa: Local Feature Matching Revisited
Apr 6, 2026David Nordström, Johan Edstedt, Georg Bökman +6Harder Better Faster Denser Feature Matching Structure-From-Motion
Chalmers University of Technology · Linköping University · University of Amsterdam +1
Probing and Leveraging Video Diffusion Transformer Features for Robust Point Tracking
Dec 23, 2025Soowon Son, Honggyu An, Jisu Nam +73D Tracking Video Diffusion Models
KAIST AI · Google DeepMind
RoMa v2: Harder Better Faster Denser Feature Matching
Nov 19, 2025Johan Edstedt, David Nordström, Yushan Zhang +7Harder Better Faster Denser Feature Matching Dense Prediction
Linköping University · Chalmers University of Technology · University of Amsterdam +1
Structure-Guided Self-Supervised Matching for One-Shot Medical Landmark Detection
Mar 3, 2022Qingsong Yao, Zhen Huang, Ao Wang +4One-Shot Medical Landmark Detection Harder Better Faster Denser Feature Matching
Soochow School of Artificial Intelligence Renmin University of China · Department of Computer Science University of Science and Technology of China · School of Biomedical Engineering University of Science and Technology of China +3

Sep 30, 2026, cs.CVJ/K move · Enter open · S save

FAST: Flow Any Scene Transformer

Yongjian Zhang, Longguang Wang, Zhuo Song, Zhiheng Fu+2

School of Electronics and Communication Engineering, the Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University, Shenzhen, China · Hong Kong Polytechnic University, HKSAR, China · School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China

Harder Better Faster Denser Feature Matching Recent Vision Foundation Models Cross-Attention Scene Understanding Transformer Architectures

Open paper AskPDF arXiv

Scaling has become a primary driver of progress in language and vision foundation models, yet its role in precise correspondence matching remains underexplored. In this work, we present Flow Any Scene Transformer (FAST), a scalable correspondence model driven by two key insights. First, we reveal that the query-key projections inside single-view vision foundation models encode a coarse yet reusable prior for cross-view matching. Second, reusing these pretrained projections in cross-attention form yields a highly effective initialization for a ViT-based matcher built from a single-view encoder. Guided by these insights, we build FAST upon a vanilla single-view foundation model, utilizing a zero-parameter rewiring strategy to convert selected self-attention layers into cross-attention for cross-view interaction. This design allows ViT-based matchers to scale with advances in single-view foundation models, bypassing the need for a dedicated pair-centric pretraining stage. To fully unlock the scaling potential of this formulation, we assemble a 6-million-pair training corpus for general-purpose dense 2D displacement estimation across diverse co-visible image pairs. Extensive experiments demonstrate that FAST achieves state-of-the-art performance across a wide range of benchmarks, while scaling favorably with both backbone size and training data.

Momentum

Related topics

Latest papers 37