Distinctive Image Features from Scale-Invariant Keypoints

2004/06/02 by David Lowe, David G. Lowe · 257 citations
Computer Science · Engineering · #Advanced Image and Video Retrieval Techniques #Image and Object Detection Techniques #Robotics and Sensor-Based Localization

paper · doi:10.1023/b:visi.0000029664.99615.94

openalex publication_date 2004/06/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/31

Cited by

• Gaussians on Fire: High-Frequency Reconstruction of Flames
• Multimodal remote sensing change detection: An image matching perspective
• Hybrid SIFT-SNN for Efficient Anomaly Detection of Traffic Flow-Control Infrastructure
• Unlocking Zero-shot Potential of Semi-dense Image Matching via Gaussian Splatting
• Selective Disk Bispectrum: A Complete and Rotation Invariant Image Descriptor
• Real-Time Object Tracking with On-Device Deep Learning for Adaptive Beamforming in Dynamic Acoustic Environments
• C3Po: Cross-View Cross-Modality Correspondence by Pointmap Prediction
• FeRA: Frequency-Energy Constrained Routing for Effective Diffusion Adaptation Fine-Tuning
• SPIDER: Spatial Image CorresponDence Estimator for Robust Calibration
• iGaussian: Real-Time Camera Pose Estimation via Feed-Forward 3D Gaussian Splatting Inversion
• Find the Leak, Fix the Split: Cluster-Based Method to Prevent Leakage in Video-Derived Datasets
• Uni-Hand: Universal Hand Motion Forecasting in Egocentric Views
• CLIDD: Cross-Layer Independent Deformable Description for Efficient and Discriminative Local Feature Representation
• DiffRegCD: Integrated Registration and Change Detection with Diffusion Features
• Wid3R: Wide Field-of-View 3D Reconstruction via Camera Model Conditioning
• LeCoT: revisiting network architecture for two-view correspondence pruning
• Global Multiple Extraction Network for Low-Resolution Facial Expression Recognition
• Improving Multi-View Reconstruction via Texture-Guided Gaussian-Mesh Joint Optimization
• MID: A Self-supervised Multimodal Iterative Denoising Framework
• VisionCAD: An Integration-Free Radiology Copilot Framework
• Scaling Image Geo-Localization to Continent Level
• Robust RPC Bundle Adjustment for Multi-Date Satellite Imagery with Season-Invariant Correspondences
• VGGT-Det: Mining VGGT Internal Priors for Sensor-Geometry-Free Multi-View Indoor 3D Object Detection
• RaCo: Ranking and Covariance for Practical Learned Keypoints
• Understanding and Optimizing Attention-Based Sparse Matching for Diverse Local Features
• XRefine: Attention-Guided Keypoint Match Refinement
• High-throughput Verticillium wilt detection in cotton: A comparative study of faster R-CNN and YOLOv11
• Hybrid Vision Servoing with Depp Alignment and GRU-Based Occlusion Recovery
• GroundLoc: Efficient Large-Scale Outdoor LiDAR-Only Localization
• Reanimating the past: From historical collections of the placenta and uterus to modern imaging, machine learning, and multiscale modeling
• LightGlueStick: a Fast and Robust Glue for Joint Point-Line Matching
• PlanarTrack: A high-quality and challenging benchmark for large-scale planar object tracking
• Dynamically Detect and Fix Hardness for Efficient Approximate Nearest Neighbor Search
• Depth-Supervised Fusion Network for Seamless-Free Image Stitching
• Freehand 3D Ultrasound Imaging: Sim-in-the-Loop Probe Pose Optimization via Visual Servoing
• UREM: A High-performance Unified and Resilient Enhancement Method for Multi- and High-Dimensional Indexes
• PoseCrafter: Extreme Pose Estimation with Hybrid Video Synthesis
• Ninja Codes: Neurally Generated Fiducial Markers for Stealthy 6-DoF Tracking
• A Renaissance of Explicit Motion Information Mining from Transformers for Action Recognition
• Joint Multi-Condition Representation Modelling via Matrix Factorisation for Visual Place Recognition
• Leveraging AV1 motion vectors for Fast and Dense Feature Matching
• DeepDetect: Learning All-in-One Dense Keypoints
• CuSfM: CUDA-Accelerated Structure-from-Motion
• C4D: 4D Made from 3D through Dual Correspondences
• Exploring Image Representation with Decoupled Classical Visual Descriptors
• Leveraging Cycle-Consistent Anchor Points for Self-Supervised RGB-D Registration
• Scaling Vision Transformers for Functional MRI with Flat Maps
• Through the Lens of Doubt: Robust and Efficient Uncertainty Estimation for Visual Place Recognition
• Accelerated Feature Detectors for Visual SLAM: A Comparative Study of FPGA vs GPU
• MultiFoodhat: A potential new paradigm for intelligent food quality inspection
• Guided Image Feature Matching using Feature Spatial Order
• An Efficient Deep Template Matching and In-Plane Pose Estimation Method via Template-Aware Dynamic Convolution
• LTGS: Long-Term Gaussian Scene Chronology From Sparse View Updates
• The Orbitoscope, a six-axis macro-imaging robot for photogrammetric 3D-digitization of insects and other small specimens
• A Comparative Study of Vision Transformers and CNNs for Few-Shot Rigid Transformation and Fundamental Matrix Estimation
• OpenFLAME: Federated Visual Positioning System to Enable Large-Scale Augmented Reality Applications
• Panorama: Fast-Track Nearest Neighbors
• Reward driven discovery of the optimal microstructure representations with invariant variational autoencoders
• Benchmarking Egocentric Visual-Inertial SLAM at City Scale
• Hy-Facial: Hybrid Feature Extraction by Dimensionality Reduction Methods for Enhanced Facial Expression Classification
• SAGE: Spatial-visual Adaptive Graph Exploration for Visual Place Recognition
• TTT3R: 3D Reconstruction as Test-Time Training
• Robust Visual Localization in Compute-Constrained Environments by Salient Edge Rendering and Weighted Hamming Similarity
• Similarity-Aware Selective State-Space Modeling for Semantic Correspondence
• Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networks
• RANSAC Scoring Done Right
• OracleGS: Grounding Generative Priors for Sparse-View Gaussian Splatting
• ARD-REFSM: Enhancing Reflection Symmetry Detection with Asymmetric Denoising and Rotation Equivariance
• Counting Grid Aggregation for Event Retrieval and Recognition
• Scalable and Sustainable Dry Microfabrication Enabled by High-Precision and Wafer-Scale Transfer Lithography of Commercial Photoresists
• Dark3R: Learning Structure from Motion in the Dark
• Camera Pose Refinement via 3D Gaussian Splatting
• Identifying Adaptive Footprints in the Presence of Demographic Uncertainty
• Effective scaling registration approach by imposing the emphasis on the scale factor
• KAMERA: Enhancing Aerial Surveys of Ice-associated Seals in Arctic Environments
• Hierarchical Neural Semantic Representation for 3D Semantic Correspondence
• OrthoLoC: UAV 6-DoF Localization and Calibration Using Orthographic Geodata
• Automatic Intermodal Loading Unit Identification using Computer Vision: A Scoping Review
• SPFSplatV2: Efficient Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views
• HotSpotter - Patterned Species Instance Recognition
• Aberrant cortex contractions impact mammalian oocyte quality
• Geometric Image Synchronization with Deep Watermarking
• PRISM: Product Retrieval In Shopping Carts using Hybrid Matching
• Scale and Rotation Estimation of Similarity-Transformed Images via Cross-Correlation Maximization Based on Auxiliary Function Method
• SWA-PF: Semantic-Weighted Adaptive Particle Filter for Memory-Efficient 4-DoF UAV Localization in GNSS-Denied Environments
• Gaussian Alignment for Relative Camera Pose Estimation via Single-View Reconstruction
• MFAF: An EVA02-Based Multi-scale Frequency Attention Fusion Method for Cross-View Geo-Localization
• OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling
• The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solvers
• Towards the Distributed Large-scale k-NN Graph Construction by Graph Merge
• Calib3R: A 3D Foundation Model for Multi-Camera to Robot Calibration and 3D Metric-Scaled Scene Reconstruction
• Deep Learning for Free-Hand Sketch: A Survey
• Good Deep Features to Track: Self-Supervised Feature Extraction and Tracking in Visual Odometry
• Understanding the Limitations of CNN-based Absolute Camera Pose\n Regression
• Robotic Tactile Perception of Object Properties: A Review
• EDFFDNet: Towards Accurate and Efficient Unsupervised Multi-Grid Image Registration
• Australian Supermarket Object Set (ASOS): A Benchmark Dataset of Physical Objects and 3D Models for Robotics and Computer Vision
• Block-Sparse Global Attention for Efficient Multi-View Geometry Transformers
• Learning Multi-Stage Tasks with One Demonstration via Self-Replay
• TemporalFlowViz: Parameter-Aware Visual Analytics for Interpreting Scramjet Combustion Evolution
• Comparative Evaluation of Traditional and Deep Learning Feature Matching Algorithms using Chandrayaan-2 Lunar Data
• Towards Open World Detection: A Survey
• Stitching the Story: Creating Panoramic Incident Summaries from Body-Worn Footage
• Global-to-Local or Local-to-Global? Enhancing Image Retrieval with Efficient Local Search and Effective Global Re-ranking
• On sources to variabilities of simple cells in the primary visual cortex: A principled theory for the interaction between geometric image transformations and receptive field responses
• MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement
• Articulated Object Estimation in the Wild
• Multi-Focused Video Group Activities Hashing
• Encoder-Only Image Registration
• GelSLAM: A Real-time, High-Fidelity, and Robust 3D Tactile SLAM System
• Teaching Robots to Do Object Assembly using Multi-modal 3D Vision
• Radially Distorted Homographies, Revisited
• Real-time Collaboration Between Mixed Reality Users in Geo-referenced Virtual Environment
• Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understanding
• MSMVD: Exploiting Multi-scale Image Features via Multi-scale BEV Features for Multi-view Pedestrian Detection
• Seam360GS: Seamless 360° Gaussian Splatting from Real-World Omnidirectional Images
• Automated Feature Tracking for Real-Time Kinematic Analysis and Shape Estimation of Carbon Nanotube Growth
• Spatial Policy: Guiding Visuomotor Robotic Manipulation with Spatial-Aware Modeling and Reasoning
• CellINR: Implicitly Overcoming Photo-induced Artifacts in 4D Live Fluorescence Microscopy
• LIFT: Learned Invariant Feature Transform
• Minimally Supervised Feature Selection for Classification (Master's Thesis, University Politehnica of Bucharest)
• HEp-2 Cell Image Classification with Deep Convolutional Neural Networks
• Reliable Multi-view 3D Reconstruction for `Just-in-time' Edge Environments
• Sensing, Social, and Motion Intelligence in Embodied Navigation: A Comprehensive Survey
• A Generic Framework for Assessing the Performance Bounds of Image\n Feature Detectors
• Large-Scale Image Retrieval with Attentive Deep Local Features
• Opening the Black Box of 3D Reconstruction Error Analysis with VECTOR
• Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer
• Viewpoint Invariant Object Detector
• Matching objects across the textured-smooth continuum
• Deep learning-driven investigation of nanoplastic impacts on soil protist behavior in soil chips
• A smile I could recognise in a thousand: Automatic identification of identity from dental radiography
• Graph-based Thermal-Inertial SLAM with Probabilistic Neural Networks
• Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks
• Data Shift of Object Detection in Autonomous Driving
• Feature Learning by Multidimensional Scaling and its Applications in Object Recognition
• Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose
• Neural Probabilistic System for Text Recognition
• A comparative study of plant phenotyping workflows based on three-dimensional reconstruction from multi-view images
• Axis-level Symmetry Detection with Group-Equivariant Representation
• Multi-View Large-Scale Bundle Adjustment Method for High-Resolution Satellite Images
• A Sub-Pixel Multimodal Optical Remote Sensing Images Matching Method
• Deep Sparse Subspace Clustering
• Compact Approximation for Polynomial of Covariance Feature
• Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondence
• LiPo-LCD: Combining Lines and Points for Appearance-based Loop Closure Detection
• Topological Structure Description for Artcode Detection Using the Shape of Orientation Histogram
• Image Retrieval with Fisher Vectors of Binary Features
• LATCH: Learned Arrangements of Three Patch Codes
• Fast, Accurate Thin-Structure Obstacle Detection for Autonomous Mobile Robots
• ImageNet MPEG-7 Visual Descriptors - Technical Report
• Salient Object Detection: A Distinctive Feature Integration Model
• PatchGame: Learning to Signal Mid-level Patches in Referential Games
• Harnessing Input-Adaptive Inference for Efficient VLN
• Learning to Hallucinate Face Images via Component Generation and Enhancement
• Sparse and redundant signal representations for x-ray computed tomography
• A Performance Evaluation of Local Features for Image Based 3D Reconstruction
• Improving Place Recognition Using Dynamic Object Detection
• Mem4D: Decoupling Static and Dynamic Memory for Dynamic Scene Reconstruction
• Semi-supervised Multiscale Matching for SAR-Optical Image
• Dynamicity and Durability in Scalable Visual Instance Search
• Are visual dictionaries generalizable?
• Deep Learning for Single-View Instance Recognition
• Efficient Multimedia Similarity Measurement Using Similar Elements
• Dynamic Concept Composition for Zero-Example Event Detection
• Robust Image Stitching with Optimal Plane
• EndoMatcher: Generalizable Endoscopic Image Matcher via Multi-Domain Pre-training for Robot-Assisted Surgery
• TSMS-SAM2: Multi-scale Temporal Sampling Augmentation and Memory-Splitting Pruning for Promptable Video Object Segmentation and Tracking in Surgical Scenarios
• Separable Four Points Fundamental Matrix
• Deep Learning-based Scalable Image-to-3D Facade Parser for Generating Thermal 3D Building Models
• PIS3R: Very Large Parallax Image Stitching via Deep 3D Reconstruction
• Asymmetric activation of retinal ON and OFF pathways by AOSLO raster-scanned visual stimuli
• DOMR: Establishing Cross-View Segmentation via Dense Object Matching
• Infrared face recognition: a comprehensive review of methodologies and\n databases
• Content-Based Bird Retrieval using Shape context, Color moments and Bag of Features
• Unsupervised Metric Relocalization Using Transform Consistency Loss
• COFFEE: A Shadow-Resilient Real-Time Pose Estimator for Unknown Tumbling Asteroids using Sparse Neural Networks
• A Review of Visual Odometry Methods and Its Applications for Autonomous Driving
• Learned versus Hand-Designed Feature Representations for 3d Agglomeration
• Contextual Action Recognition with R*CNN
• Learning Spread-out Local Feature Descriptors
• SGAD: Semantic and Geometric-aware Descriptor for Local Feature Matching
• Evolutionary Paradigms in Histopathology Serial Sections technology
• CVD-SfM: A Cross-View Deep Front-end Structure-from-Motion System for Sparse Localization in Multi-Altitude Scenes
• Saliency based Semi-supervised Learning for Orbiting Satellite Tracking
• GeoMoE: Divide-and-Conquer Motion Field Modeling with Mixture-of-Experts for Two-View Geometry
• Weakly Supervised Virus Capsid Detection with Image-Level Annotations in Electron Microscopy Images
• Learn by Observation: Imitation Learning for Drone Patrolling from Videos of A Human Navigator
• Towards Robust Semantic Correspondence: A Benchmark and Insights
• 3D Reconstruction via Incremental Structure From Motion
• A Data-driven Approach for Human Pose Tracking Based on Spatio-temporal Pictorial Structure
• Working hard to know your neighbor's margins: Local descriptor learning loss
• VMatcher: State-Space Semi-Dense Local Feature Matching
• MatchBench: An Evaluation of Feature Matchers
• Modality-Aware Feature Matching: A Comprehensive Review of Single- and Cross-Modality Techniques
• Estimating 2D Camera Motion with Hybrid Motion Basis
• Efficient Spatial-Temporal Modeling for Real-Time Video Analysis: A Unified Framework for Action Recognition and Object Tracking
• Moiré Zero: An Efficient and High-Performance Neural Architecture for Moiré Removal
• PanoSplatt3R: Leveraging Perspective Pretraining for Generalized Unposed Wide-Baseline Panorama Reconstruction
• Detection Method Based on Automatic Visual Shape Clustering for Pin-Missing Defect in Transmission Lines
• Image Recognition Using Scale Recurrent Neural Networks
• Deep Learning Representation using Autoencoder for 3D Shape Retrieval
• Impact of Underwater Image Enhancement on Feature Matching
• A Reconstruction Error Formulation for Semi-Supervised Multi-task and Multi-view Learning
• ST-DAI: Single-shot 2.5D Spatial Transcriptomics with Intra-Sample Domain Adaptive Imputation for Cost-efficient 3D Reconstruction
• Visual Odometry Revisited: What Should Be Learnt?
• Vision-based system identification and 3D keypoint discovery using dynamics constraints
• ProNet: Learning to Propose Object-specific Boxes for Cascaded Neural Networks
• Reconstructing Sinus Anatomy from Endoscopic Video -- Towards a Radiation-free Approach for Quantitative Longitudinal Assessment
• RAID: A Relation-Augmented Image Descriptor
• Aggregating Deep Convolutional Features for Image Retrieval
• A Sparse Coding Interpretation of Neural Networks and Theoretical Implications
• SK-Net: Deep Learning on Point Cloud via End-to-end Discovery of Spatial Keypoints
• Computer-Aided Colorectal Tumor Classification in NBI Endoscopy Using CNN Features
• 4D Cardiac Ultrasound Standard Plane Location by Spatial-Temporal Correlation
• Robust SfM with Little Image Overlap
• ADAGIO: Fast Data-aware Near-Isometric Linear Embeddings
• 6-DoF Object Pose from Semantic Keypoints
• GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs
• FRAM: Frobenius-Regularized Assignment Matching with Mixed-Precision Computing
• Cross Spatial Temporal Fusion Attention for Remote Sensing Object Detection via Image Feature Matching
• Target Driven Instance Detection
• TROVE Feature Detection for Online Pose Recovery by Binocular Cameras
• Superpixel-based Two-view Deterministic Fitting for Multiple-structure Data
• Pose Graph Optimization for Unsupervised Monocular Visual Odometry
• Kernel Selection using Multiple Kernel Learning and Domain Adaptation in Reproducing Kernel Hilbert Space, for Face Recognition under Surveillance Scenario
• Improving the HardNet Descriptor
• Graph based Nearest Neighbor Search: Promises and Failures
• End-to-end learning of keypoint detection and matching for relative pose estimation
• LONG3R: Long Sequence Streaming 3D Reconstruction
• VLASE: Vehicle Localization by Aggregating Semantic Edges
• Towards an Automatic System for Extracting Planar Orientations from Software Generated Point Clouds
• Window-Object Relationship Guided Representation Learning for Generic Object Detections
• cvpaper.challenge in 2016: Futuristic Computer Vision through 1,600 Papers Survey
• DCTM: Discrete-Continuous Transformation Matching for Semantic Flow
• Robust Place Recognition using an Imaging Lidar
• Using depth information and colour space variations for improving outdoor robustness for instance segmentation of cabbage
• Megalithic statue (moai) production on Rapa Nui (Easter Island, Chile)
• Joint Spatial and Layer Attention for Convolutional Networks
• Joint Deformable Registration of Large EM Image Volumes: A Matrix Solver\n Approach
• Sparseness helps: Sparsity Augmented Collaborative Representation for Classification
• Retrieval and Localization with Observation Constraints
• Understanding Deep Image Representations by Inverting Them
• Local Unsupervised Learning for Image Analysis
• Visual-inertial navigation, mapping and localization: A scalable real-time causal approach
• Scene Invariant Crowd Segmentation and Counting Using Scale-Normalized\n Histogram of Moving Gradients (HoMG)
• Learning Multi-Scale Deep Features for High-Resolution Satellite Image Classification
• Generative Adversarial Data Programming
• Image‐based 3D Modelling: A Review
• <scp>3D LiDAR SLAM</scp>: A survey
• A local fingerprinting approach for audio copy detection
• Adaptive color-corrected multicolor space enhancement network for underwater image enhancement
• Microassembly of multi-material and 3D integration enabled by programmable and universal high-precision micro-transfer printing
• Optimising Image Feature Extraction and Selection: A Comprehensive Review With Spark Case Studies
• Evaluating Soccer Player: from Live Camera to Deep Reinforcement Learning
• A Benchmark Comparison of Visual Place Recognition Techniques for Resource-Constrained Embedded Platforms
• An Intelligent Hybrid Model for Identity Document Classification