awesome-image-registration

Awesome Image Registration

A curated list of image registration related books, papers, videos, and toolboxes

Image registration is the process of transforming different sets of data into one coordinate system. Data may be multiple photographs, and from different sensors, times, depths, or viewpoints.

It is used in computer vision, medical imaging, military automatic target recognition, compiling and analyzing images and data from satellites. Registration is necessary in order to be able to compare or integrate the data obtained from different measurements.

We use another project to automatically track updates to IR papers, click on IR-paper-update-tracker if you need it.

Please note that if this page does not display the full content, please visit the official homepage for full information.

How to contact us

We have QQ Group 【配准萌新交流群】（已满3000人）869211738 欢迎加入【配准萌新交流（二群)】 929134506 and Wechat Group 【配准交流群】（已满员） for comunications.

More items will be added to the repository. Please feel free to suggest other key resources by opening an issue report, submitting a pull request, or dropping me an email @ ([email protected]). Enjoy reading!

Paper Lists

• 2020s: 2026 2025 2024 2023 2022 2021 2020
• 2010s: 2019 2018 2017 2016 2015 2014 2013 2012 2011 2010
• 2000s: 2009 2008 2007 2006 2005 2004 2003 2002 2001 2000
• 1990s: 1999 1998 1997 1996 1995 1994 1993 1992 1991 1990
• 1980s & earlier: 1989 1988 1987 1986 1985 1984 1983 1982 1981 1980 1979 1977 1975 1972

Learning Resources

• Datasets
• Competitions
• Toolbox
• Books
• Tutorials
• Blogs
• Courses Seminars and Videos
• Conferences and Workshops
• Journals

---

Paper Lists

A paper list of image registration.

Keywords

medi.: medical image | nat.: natural image | rs.: remote sensing | pc.: point cloud

data.: dataset  |   dep.: deep learning

oth.: other, including correspondence, mapping, matching, alignment...

Statistics: :fire: code is available & stars >= 100  |  :star: citation >= 50

Update log

Last updated: 2026/10/17

2026/10/17 - merge 179 new papers from IR-Papers.md, including 2026 updates, NeurIPS 2025, and historical supplements.

2026/05/21 - major update: merge ~3,500 papers from IR-Papers.md, extend coverage from 2026 to 1972 (51 years), add new venues (TMI, JBHI, IPMI, MM, IJCV, etc.), unify paper format, and remove duplicates.

2025/09/21 - update recent papers

2025/04/25 - update recent papers and add the repository link of Awesome-Medical-Image-Registration

2024/12/03 - update recent papers

2024/04/30 - update recent papers on TPAMI/MICCAI/CVPR/ICCV/ECCV/AAAI/NeurIPS/MIA/ICLR

2023/03/02 - add papers according to 3D-PointCloud, update recent papers on CVPR/ECCV 2022

2022/07/27 - update recent papers on ECCV 2022

2022/07/14 - add the corresponding open source code for the 2022 papers

2022/07/12 - update recent papers on AAAI 2022 and add information about competitions

2022/06/19 - update recent TPAMI papers (2017-2021) about image registration according to dblp search engine, update recent MICCAI papers about image registration according to MICCAI-OpenSourcePapers.

2022/06/18 - update recent papers (2017-2021) on CVPR/ICCV/ECCV/AAAI/NeurIPS/MIA about image registration according to dblp search engine.

2022/06/18 - update papers (2020-2022) about point cloud registration from awesome-point-cloud-analysis-2023.

2020/04/20 - update recent papers (2017-2020) about point cloud registration and make some diagram about history of image registration.

2026

CVPR

• BiFM: Bidirectional Flow Matching for Few-Step Image Editing and Generation. [PUB] [dep.]
• BluRef: Unsupervised Image Deblurring with Dense-Matching References. [PUB]
• Can We Build Scene Graphs, Not Classify Them? FlowSG: Progressive Image-Conditioned Scene Graph Generation with Flow Matching. [PUB] [dep.]
• C-GenReg: Training-Free 3D Point Cloud Registration by Multi-View-Consistent Geometry-to-Image Generation with Probabilistic Modalities Fusion. [PUB] [pc.] [dep.]
• CRFT: Consistent-Recurrent Feature Flow Transformer for Cross-Modal Image Registration. [PUB] [CODE] [medi.] [rs.] [dep.] [oth.]
• Cross-Instance Gaussian Splatting Registration via Geometry-Aware Feature-Guided Alignment. [PUB] [oth.]
• Disentangle-then-Align: Non-Iterative Hybrid Multimodal Image Registration via Cross-Scale Feature Disentanglement. [PUB] [medi.] [dep.] [oth.]
• DualReg: Dual-Space Filtering and Reinforcement for Rigid Registration. [PUB]
• Dynamic Stream Network for Combinatorial Explosion Problem in Deformable Medical Image Registration. [PUB] [medi.]
• Efficient All-Pairs Correlation Volume Sampling for Optical Flow Estimation. [PUB] [data.] [dep.] [oth.]
• Feed-forward Gaussian Registration for Head Avatar Creation and Editing. [PUB] [dep.]
• Flow4DGS-SLAM: Optical Flow-Guided 4D Gaussian Splatting SLAM. [PUB] [pc.] [oth.]
• FlowDIS: Language-Guided Dichotomous Image Segmentation with Flow Matching. [PUB] [CODE] [medi.] [data.]
• FlowFM: Advancing Dark Optical Flow Estimation with Flow Matching. [PUB] [oth.]
• FlowPalm: Optical Flow Driven Non-Rigid Deformation for Geometrically Diverse Palmprint Generation. [PUB] [data.] [oth.]
• Frequency-Aware Flow Matching for High-Quality Image Generation. [PUB]
• From Contrast to Consistency: Rethinking Event-based Continuous-Time Optical Flow Estimation. [PUB] [dep.] [oth.]
• FUSER: Feed-Forward Multiview 3D Registration Transformer and SE(3)$N$ Diffusion Refinement. [PUB] [pc.] [dep.]
• FusionRegister: Every Infrared and Visible Image Fusion Deserves Registration. [PUB]
• Generalized-CVO: Fast and Correspondence-Free Local Point Cloud Registration with Second Order Riemannian Optimization. [PUB] [pc.]
• GeniNav: Generative Model Driven Image-Goal Navigation via Imagination-Guided Consistency Flow Matching. [PUB]
• GM-R2: Generative Matching Learning for Unsupervised Geometric Representation and Registration. [PUB]
• Hg-I2P: Bridging Modalities for Generalizable Image-to-Point-Cloud Registration via Heterogeneous Graphs. [PUB] [CODE] [pc.] [data.]
• LAOF: Robust Latent Action Learning with Optical Flow Constraints. [PUB] [dep.] [oth.]
• Learning Diffeomorphism for Medical Image Registration with Time-Embedded Architectures Using Semigroup Regularization. [PUB] [medi.]
• Match-and-Fuse: Consistent Generation from Unstructured Image Sets. [PUB]
• MHopReg: Efficient Hierarchical Multi-Hop Graph Search for Point Cloud Registration. [PUB] [pc.]
• MorphSeek: Fine-grained Latent Representation-Level Policy Optimization for Deformable Image Registration. [PUB] [medi.] [pc.] [dep.] [oth.]
• Optical Flow Matching: Reframing Optical Flow as Continuous Transport Dynamics. [PUB] [oth.]
• PiLoT: Neural Pixel-to-3D Registration for UAV-based Ego and Target Geo-localization. [PUB] [CODE] [rs.] [pc.] [data.]
• ReFlow: Self-correction Motion Learning for Dynamic Scene Reconstruction. [PUB] [oth.]
• Registration-Free Learnable Multi-View Capture of Faces in Dense Semantic Correspondence. [PUB] [dep.]
• Rethinking 2D-3D Registration: A Novel Network for High-Value Zone Selection and Representation Consistency Alignment. [PUB] [pc.]
• Scaling Multi-Identity Consistency for Image Customization via Multi-to-Multi Matching Paradigm. [PUB] [CODE] [data.] [dep.]
• Stitch-a-Demo: Creating Video Demonstrations from Multistep Descriptions. [PUB] [oth.]
• STiTch: Semantic Transition and Transportation in Collaboration for Training-Free Zero-Shot Composed Image Retrieval. [PUB] [dep.] [oth.]
• SuP: Sub-cloud Driven Point Cloud Registration. [PUB] [pc.]
• U2Flow: Uncertainty-Aware Unsupervised Optical Flow Estimation. [PUB] [oth.]

ECCV

• AdaBridge-SR: Adaptive Bridge Matching for Real-World Image Super-Resolution. [PUB] [nat.]
• AnyMatch: Supercharging Universal Multi-modal Image Matching with Large-Scale Single-View Images. [PUB] [nat.] [data.] [dep.] [oth.]
• CasaMaestro: Multi-view Panoramas for House-Scale 3D Reconstruction. [PUB] [pc.]
• DiTailed: Ensuring Visual Object Consistency in Text-Image-to-Image Flow Matching Models. [PUB] [data.]
• Ex-Sim(3)-Reg: 2D-3D Correspondence Pruning via Extended Sim(3) Registration. [PUB] [dep.]
• FlowCIR: Semantic Transport via Flow Matching for Zero-Shot Composed Image Retrieval. [PUB]
• FlowInOne: Unifying Multimodal Generation as Image-in, Image-Out Flow Matching. [PUB] [data.]
• FlowPainter: Inpainting Optical Flow via Confidence-Guided Completion. [PUB] [oth.]
• Flow Straight to Reality: Perceptually Consistent Flow Matching for Efficient Image Restoration. [PUB] [dep.]
• Foundation-Guided Representation Alignment for Multimodal Medical Image Registration. [PUB] [medi.]
• FreeFlow: A Bias-Free Hierarchical Transformer for Optical Flow Estimation. [PUB] [dep.] [oth.]
• GraphCPD: Coherent Point Drift for Point Cloud Registration via Graph Signal Processing. [PUB] [pc.]
• MegaFlow: Zero-Shot Large Displacement Optical Flow. [PUB] [data.] [dep.] [oth.]
• OCA: ODE-Driven Cross-Attention for Image-to-Point-Cloud Registration. [PUB] [data.] [dep.]
• On the Real-World Generalisability of Optical Flow Models. [PUB] [data.] [oth.]
• Parsimonious Flow Matching for Efficient Image Generation. [PUB]
• PGCR: Pose-Geometry Coupled Reasoning for Image-to-Point Cloud Registration. [PUB] [pc.]
• Pixel-Wise Geo-Registration of Drone Images. [PUB] [rs.] [pc.] [data.] [oth.]
• RegHead: Non-humanoid Head Blendshapes via Feed-Forward Registration. [PUB] [data.] [dep.]
• Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching. [PUB] [pc.]
• Revisiting Avatar-as-Image: High-Fidelity Registration is All You Need. [PUB] [pc.] [dep.]
• RTE-FM-Dehazer: Radiative Transfer Equation Inspired Flow Matching for Real-World Image Dehazing. [PUB] [nat.]
• SLAIR: Structured Latent Flow Matching for All-in-One Image Restoration. [PUB]
• Stitched Embeddings: A Unified Latent Space for 3D Garments and 2D Patterns. [PUB]
• Structured SIR: Efficient and Expressive Importance-Weighted Inference for High-Dimensional Image Registration. [PUB] [medi.]
• Triangular Consistency as a Universal Constraint for Learning Optical Flow. [PUB] [oth.]
• Tuning Real-World Image Restoration at Inference: A Test-Time Scaling Paradigm for Flow Matching Models. [PUB] [nat.]
• Two-Parameter Flow Map Learning for Continuous-Time Diffeomorphic Image Registration. [PUB]
• UniStitch: Unifying Semantic and Geometric Features for Image Stitching. [PUB] [dep.] [oth.]
• Unsupervised Point Cloud Registration via Training-Time Semantic Guidance. [PUB] [pc.]
• WiFlow: Estimating Optical Flow Using WiFi Channel State Information. [PUB] [data.] [oth.]
• XPos3R: Cross-Modal Transformer for Intraoperative 2D/3D Registration. [PUB] [medi.] [pc.] [dep.]

ICLR

• A Scalable Distributed Framework for Multimodal GigaVoxel Image Registration. [PUB] [medi.] [pc.] [data.] [dep.]
• ARFlow: Auto-regressive Optical Flow Estimation for Arbitrary-Length Videos via Progressive Next-Frame Forecasting. [PUB] [oth.]
• Credit-Budgeted ICPC-Style Coding: When Agents Must Pay for Every Decision. [PUB] [data.]
• DeepFRC: An End-to-End Deep Learning Model for Functional Registration and Classification. [PUB] [dep.]
• Functional MRI Time Series Generation via Wavelet-Based Image Transform and Spectral Flow Matching for Brain Disorder Identification. [PUB] [CODE] [medi.]
• Multimodal Aligned Semantic Knowledge for Unpaired Image-text Matching. [PUB]
• Purrception: Variational Flow Matching for Vector-Quantized Image Generation. [PUB]
• RayI2P: Learning Rays for Image-to-Point Cloud Registration. [PUB] [pc.]
• Reliable Evaluation of MRI Motion Correction: Dataset and Insights. [PUB] [medi.] [data.] [dep.]
• RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo. [PUB] [data.] [oth.]
• SenseFlow: Scaling Distribution Matching for Flow-based Text-to-Image Distillation. [PUB] [CODE] [data.] [dep.]
• Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator. [PUB] [oth.]
• Unified Brain Surface and Volume Registration. [PUB] [medi.]
• WAFT: Warping-Alone Field Transforms for Optical Flow. [PUB] [CODE] [oth.]

AAAI

• Adaptive Agent Selection and Interaction Network for Image-to-Point Cloud Registration. [PUB]
• AerialFusion: Co-Motion-Driven Unified Registration and Fusion on Multi-modal Data Streams from Aerial View. [PUB]
• Ambiguity-aware Truncated Flow Matching for Ambiguous Medical Image Segmentation. [PUB]
• BAT: Learning Event-based Optical Flow with Bidirectional Adaptive Temporal Correlation. [PUB]
• DFMN: A Dual-feet Matching Network with Hybrid Transformer-based Feature Extractor for Unsupervised Deformable Medical Image Registration. [PUB]
• FlowAnyTime: Efficient Fine-tuning with Intra-Inter Frame Distillation for All-Weather Optical Flow Estimation. [PUB]
• Graph Flow Matching: Enhancing Image Generation with Neighbor-Aware Flow Fields. [PUB]
• Intra-Image Mining and Symmetric Maximum Concept Matching for Few Shot Out-of-Distribution Detection. [PUB] [data.]
• MCI-Net: A Robust Multi-Domain Context Integration Network for Point Cloud Registration. [PUB]
• PMPGuard: Catching Pseudo-Matched Pairs in Remote Sensing Image-Text Retrieval. [PUB] [rs.] [data.] [dep.]
• RAW-Flow: Advancing RGB-to-RAW Image Reconstruction with Deterministic Latent Flow Matching. [PUB]
• SGPFeat: Semantic and Geometric Priors for Multi-modal Image Matching. [PUB]
• SOMA: Feature Gradient Enhanced Affine-Flow Matching for SAR-Optical Registration. [PUB]
• Symmetrical Flow Matching: Unified Image Generation, Segmentation, and Classification with Score-Based Generative Models. [PUB]

TPAMI

• Bayesian Unsupervised Disentanglement of Anatomy and Geometry for Deep Groupwise Image Registration. [PUB]
• BEVTrack: Multi-View Multi-Human Registration and Tracking in the Bird's Eye View. [PUB]
• ColorPCR++: Unleash the Power of Color for Point Cloud Registration Using Hypergraph Computation. [PUB] [pc.]
• Consistency-Aware Spot-Guided Transformer for Accurate and Versatile Point Cloud Registration. [PUB]
• Distribution-to-Points Matching for Image Text Retrieval. [PUB] [dep.]
• Equivariant Bayesian Hyperspectral Imaging via Mosaiced and PAN Image Fusion. [PUB] [rs.] [data.] [dep.]
• Iterative Differential Entropy Minimization (IDEM) Method for Fine Rigid Pairwise 3D Point Cloud Registration: A Focus on the Metric. [PUB] [pc.]
• Joint Sparse Optical Flow Estimation and Keypoint Detection via Dual-task Imperative Learning. [PUB]
• Learning Efficient Meshflow and Optical Flow From Event Cameras. [PUB]
• OIF-PCR++: Point Cloud Registration via Progressive Distillation of Conditional Positional Encoding. [PUB]
• PAVM: Progressive and Adaptive Variance Minimization Algorithm for Robust Registration. [PUB] [pc.]
• Single Voter Spreading for Efficient Correspondence Grouping and 3D Registration. [PUB]
• Spike Camera Optical Flow Estimation Based on Continuous Spike Streams. [PUB] [oth.]

IJCV

• CylindFormer: Image-to-Point Cloud Registration with Cylindrical Transformer. [PUB]
• Deep Learning-Based Point Cloud Registration: A Comprehensive Survey and Taxonomy. [PUB]
• ICPE-FAS: Instance and Category Prompts Engineering for Generalizable Face Anti-Spoofing. [PUB]
• IterRF: Iterative and Interpretable Mutual Enhancement for Joint Multi-Modal Image Registration and Fusion. [PUB]
• Robust Partial-to-Partial Point Cloud Registration with Overlapping Mask Learning. [PUB] [pc.]
• Vector-Symbolic Architecture for Event-Based Optical Flow. [PUB] [CODE] [dep.] [oth.]

TMI

• A 3-D Cross-Modal Keypoint Descriptor for MR-US Matching and Registration. [PUB] [CODE] [medi.] [data.]
• Adaptive Conditional Contrast-Agnostic Deformable Image Registration With Uncertainty Estimation. [PUB] [CODE] [medi.] [dep.] [oth.]
• Biomechanics-Informed Non-Rigid Medical Image Registration With Elasticity Theories. [PUB] [CODE] [medi.] [pc.] [dep.] [oth.]
• CASHNet: Context-Aware Semantics-Driven Hierarchical Network for Hybrid Diffeomorphic CT-CBCT Image Registration. [PUB] [CODE]
• CIM-VTP: Correlation-Guided Image Modeling With Visual-Textual Task Prompt for Universal Medical Image Registration. [PUB] [CODE] [medi.] [dep.]
• Diff-Def: Diffusion-Generated Deformation Fields for Conditional Atlases. [PUB]
• Dynamic Registration-Based Photoacoustic Endoscopic Temperature Imaging for Precision Interventional Thermal Therapy and Monitoring. [PUB] [medi.]
• Efficient Large-Deformation Medical Image Registration via Recurrent Dynamic Correlation. [PUB]
• EMORe: Motion-Robust 5D MRI Reconstruction via Expectation-Maximization-Guided Binning Correction and Outlier Rejection. [PUB] [medi.] [pc.]
• Head Motion Correction Based on Pilot Tone Signals in MRI: A Referenceless Method. [PUB] [medi.] [data.]
• MoE-Morph: Lightweight Pyramid Model With Heterogeneous Mixture of Experts for Deformable Medical Image Registration. [PUB] [CODE]
• Neural Optimization for Image Registration via Joint Modeling of Global Affine and Local Deformation Transformations. [PUB] [medi.] [data.] [dep.] [oth.]
• Overlap-Aware Online-Adaptive Non-Rigid Registration of Intraoperative Tissue in Minimally Invasive Surgery. [PUB] [CODE] [medi.]
• Temporal Conditioning for Longitudinal Brain MRI Registration and Aging Analysis. [PUB] [medi.] [dep.] [oth.]

MIA

• ARDMR: Adaptive recursive inference and representation disentanglement for multimodal large deformation registration. [PUB] [CODE]
• Beyond the LUMIR challenge: The pathway to foundational registration models. [PUB] [medi.] [data.] [dep.] [oth.]
• BIASNet: A bidirectional feature alignment and semantics-guided network for weakly-supervised medical image registration. [PUB] [CODE]
• BundleWarp: Enhancing white matter tractometry and morphometry with precise neuronal mapping using streamline-based nonlinear registration. [PUB]
• Calibration-free 3D-2D surface registration for image guided intervention. [PUB]
• Contrastive Discrepancy: A label-free metric for deformable image registration supporting testing-time hyperparameter selection. [PUB] [medi.]
• Data-driven registration and modeling of brain deformation for image-guided neurosurgery. [PUB] [medi.] [data.] [dep.] [oth.]
• Deformable image registration for self-supervised cardiac phase detection in cardiac magnetic resonance images of patients with various diseases. [PUB] [CODE] [medi.] [dep.]
• DVAP-Reg: Dual-view anatomical prior-driven cross-dimensional registration for spinal surgery navigation. [PUB] [CODE]
• Effective registration-free dual-phase segmentation for pancreas and pancreatic mass via symmetrical selective feature integration. [PUB] [medi.] [dep.]
• FlowLet: Conditional 3D brain MRI synthesis using wavelet flow matching. [PUB] [medi.] [dep.]
• From model based to learned regularization in medical image registration: A comprehensive review. [PUB]
• GAGM: Geometry-aware graph matching framework for weakly supervised gyral hinge correspondence. [PUB] [CODE]
• ISDR-Net: Interpretable Self-Supervised Differentiable Rendering Network for monocular dynamic sensor-head pose tracking and registration. [PUB] [dep.]
• Iterative learning for joint image denoising and motion artifact correction of 3D brain MRI. [PUB]
• Learning dual-scale context with overlap awareness for keypoint-driven partial-overlap medical image registration. [PUB] [medi.]
• ModeTv2: GPU-accelerated motion decomposition transformer for pairwise optimization in medical image registration. [PUB]
• NeuralBoneReg: An instance-specific label-free point cloud-based method for multi-modal bone surface registration. [PUB] [medi.] [pc.] [data.] [dep.]
• OphMatcher: Uncertainty-aware self-training on ophthalmic surgical videos for anatomy-constrained matching and intraoprative navigation. [PUB] [medi.]
• PIVOTS: Aligning unseen structures using preoperative to intraoperative volume-to-surface registration for liver navigation. [PUB] [medi.] [pc.] [data.] [dep.]
• Robust non-rigid image-to-patient registration for contactless dynamic thoracic tumor localization using recursive deformable diffusion models. [PUB]
• Spatio-temporal registration of multi-perspective 3D echocardiography for improved strain estimation. [PUB] [medi.]
• Two-stage robust 3D CTA-2D DSA alignment via vascular-aware rigid and pyramid-based hierarchical non-rigid registration. [PUB] [medi.] [dep.]
• Unsupervised learning of spatially varying regularization for diffeomorphic image registration. [PUB] [dep.]
• Unsupervised multimodal surface registration with geometric deep learning. [PUB] [CODE]
• UTMorph: A hybrid CNN-transformer network for weakly-supervised multimodal image registration in biopsy puncture. [PUB] [CODE]
• Vision foundation model for 3D magnetic resonance imaging segmentation, classification, and registration. [PUB]

MICCAI

• Angio-Stitch: An Unsupervised Coarse-to-Fine Framework for Sequential Stitching of Confocal Laser Endomicroscopy Images. [PUB] [medi.] [oth.]
• DreamReg: Belief-Driven World Model for 2D-3D Ultrasound Registration. [PUB] [medi.] [pc.] [dep.]
• End2Reg: Learning Task-Specific Segmentation for Markerless Registration in Spine Surgery. [PUB] [medi.] [pc.] [dep.]
• FlowReg: Reconstruction-Guided Flow Matching for Universal Spinal CT/X-Ray Registration. [PUB] [medi.]
• FSE-Reg: Enhancing 3D Deformable Registration with Frozen Large-Scale Pre-trained Segmentation Encoders. [PUB] [medi.] [dep.]
• Human-AI Collaboration for 2D/3D Registration Quality Assurance. [PUB] [medi.] [pc.]
• Intraoperative Fluoroscopy-Volume Registration Using Virtual-Supervision Skeleton Attention. [PUB] [medi.]
• Intraoperative X-Ray-Guided Tumor Tracking via Dynamic 3D/2D Registration with Task-Driven 3D Gaussian Priors. [PUB] [medi.]
• Joint Decomposition and Learned Deformation for Part-to-Whole MRI to Histology Registration. [PUB] [medi.] [dep.]
• Keypoint Correspondence Learning for CBCT-IOS Registration. [PUB] [medi.]
• KGT-Reg: Knowledge-Guided Multimodal Framework for Medical Image Registration. [PUB] [medi.]
• Latent Lessons from Histopathology: A Registration-Free Cross-Modal Supervision Framework for mpMRI-Based ISUP Grading. [PUB] [medi.]
• Learning Hierarchical Anatomy-Grounded Representation for Cross-Modal Registration. [PUB] [medi.]
• Learning Modality-Invariant Structure and Distribution Alignment for Multimodal Medical Image Registration. [PUB] [medi.]
• Making HE Histopathological Images More Colorful by Conditional Flow Matching. [PUB] [medi.]
• OPS: One-Shot Point Prompted Semantics-Aware Learning for Medical Image Registration. [PUB] [medi.]
• Optimal Steps for Fast Diffeomorphic Shape Registration. [PUB] [medi.]
• PathoMamba: Piecewise-Diffeomorphic Registration via Stiffness-Modulated State Space Dynamics. [PUB] [medi.]
• Really Need Recursion? Revisiting One-Pass Registration with Multi-Level Multi-Space Contextual Guidance. [PUB] [medi.]
• Set-Based Groupwise Registration for Variable-Length, Variable-Contrast Cardiac MRI. [PUB] [medi.] [data.] [dep.] [oth.]
• Shape-Aware Registration Without Pretraining: CT-Ultrasound Bone Surface Alignment via Instance-Level Shape Completion. [PUB] [medi.]
• SPEAR: Error-Guided Sparse Refinement for Scalable Deformable Medical Image Registration. [PUB] [medi.]
• SwallowReg: SAM-Assisted Deformable Registration with Adaptive Global-Local Features for Cine-MRI Swallowing Function Quantification. [PUB] [medi.]
• TG-OT: Topology-Guided CCTA-IVUS Registration via Optimal Transport Matching. [PUB] [medi.] [data.]
• VarDeFlow: Variational Deformation Learning with Flow Matching for Multi-organ Cross-Modality Medical Image Synthesis. [PUB] [medi.]
• Vis2Reg: Visibility-Aware Landmark-Free Geometric 3D-2D Registration for Liver Laparoscopy. [PUB] [medi.] [dep.] [oth.]

JBHI

• Cross-Correlation Rectification for Robust Deformable Registration of Brain Tumor MRI Between Preoperative and Postoperative Phases. [PUB] [medi.] [data.] [dep.] [oth.]
• Cross-Modality Image Registration via Generating Aligned Image Using Reference-Augmented Framework. [PUB] [medi.] [data.] [dep.]
• Deformable Medical Image Registration With Effective Anatomical Structure Representation and Divide-and-Conquer Network. [PUB] [medi.] [pc.] [dep.] [oth.]
• Diffusion Tensor Magnetic Resonance Image Registration Based on Parallel Dual-Channel VoxelMorph. [PUB] [medi.] [pc.] [dep.] [oth.]
• GuidedMorph: Two-Stage Deformable Registration for Breast MRI. [PUB] [medi.] [pc.] [data.] [dep.]
• LADDA: Latent Diffusion-Based Domain-Adaptive Feature Disentangling for Unsupervised Multi-Modal Medical Image Registration. [PUB] [medi.] [dep.]
• Medical Image Privacy in Federated Learning: Segmentation-Reorganization and Sparsified Gradient Matching Attacks. [PUB] [medi.]
• Resolving the Ambiguity of Complete-to-Partial Point Cloud Registration for Image-Guided Liver Surgery With Patches-to-Partial Matching. [PUB] [CODE]

KDD

• TS-Arena - A Live Forecast Pre-Registration Platform. [PUB] [data.] [dep.]

S&P

• Scalable Registration-Based Encryption from Lattices. [PUB]

2025

CVPR

• AutoURDF: Unsupervised Robot Modeling from Point Cloud Frames Using Cluster Registration. [PUB]
• Blood Flow Speed Estimation with Optical Coherence Tomography Angiography Images. [PUB] [CODE]
• Bridge Frame and Event: Common Spatiotemporal Fusion for High-Dynamic Scene Optical Flow. [PUB] [oth.]
• CamFreeDiff: Camera-free Image to Panorama Generation with Diffusion Model. [PUB]
• CARL: A Framework for Equivariant Image Registration. [PUB]
• ColabSfM: Collaborative Structure-from-Motion by Point Cloud Registration. [PUB]
• Cross-Rejective Open-Set SAR Image Registration. [PUB]
• DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework. [PUB] [CODE]
• Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration. [PUB]
• Dual Focus-Attention Transformer for Robust Point Cloud Registration. [PUB]
• EDCFlow: Exploring Temporally Dense Difference Maps for Event-based Optical Flow Estimation. [PUB]
• FloVD: Optical Flow Meets Video Diffusion Model for Enhanced Camera-Controlled Video Synthesis. [PUB]
• GraphI2P: Image-to-Point Cloud Registration with Exploring Pattern of Correspondence via Graph Learning. [PUB]
• HeMoRa: Unsupervised Heuristic Consensus Sampling for Robust Point Cloud Registration. [PUB]
• ICP: Immediate Compensation Pruning for Mid-to-high Sparsity. [PUB]
• Image Over Text: Transforming Formula Recognition Evaluation with Character Detection Matching. [PUB] [CODE]
• Implicit Correspondence Learning for Image-to-Point Cloud Registration. [PUB]
• MINIMA: Modality Invariant Image Matching. [PUB] [CODE]
• Mosaic of Modalities: A Comprehensive Benchmark for Multimodal Graph Learning. [PUB]
• Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation. [PUB]
• Multi-Modal Synergistic Implicit Image Enhancement for Efficient Optical Flow Estimation. [PUB] [oth.]
• MultiMorph: On-demand Atlas Construction. [PUB] CODE
• Optical-Flow Guided Prompt Optimization for Coherent Video Generation. [PUB]
• Panorama Generation From NFoV Image Done Right. [PUB]
• Phoenix: A Motion-based Self-Reflection Framework for Fine-grained Robotic Action Correction. [PUB] [CODE]
• Progressive Correspondence Regenerator for Robust 3D Registration. [PUB]
• RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges. [PUB]
• SACB-Net: Spatial-awareness Convolutions for Medical Image Registration. [PUB] CODE
• Shape and Texture: What Influences Reliable Optical Flow Estimation?. [PUB] [CODE] [oth.]
• Stable-SCore: A Stable Registration-based Framework for 3D Shape Correspondence. [PUB]
• Test-Time Domain Generalization via Universe Learning: A Multi-Graph Matching Approach for Medical Image Segmentation. [PUB] [CODE]
• Thin-Shell-SfT: Fine-Grained Monocular Non-rigid 3D Surface Tracking with Neural Deformation Fields. [PUB]
• Towards Realistic Example-based Modeling via 3D Gaussian Stitching. [PUB]
• Unlocking Generalization Power in LiDAR Point Cloud Registration. [PUB]
• Zero-shot RGB-D Point Cloud Registration with Pre-trained Large Vision Model. [PUB]

ICCV

• Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis. [PUB]
• Aligning Information Capacity Between Vision and Language via Dense-to-Sparse Feature Distillation for Image-Text Matching. [PUB]
• AM-Adapter: Appearance Matching Adapter for Exemplar-Based Semantic Image Synthesis In-the-Wild. [PUB]
• Anchor Token Matching: Implicit Structure Locking for Training-Free AR Image Editing. [PUB] [CODE] [dep.]
• Balanced Image Stylization with Style Matching Score. [PUB]
• Buffer-X: Towards Zero-Shot Point Cloud Registration in Diverse Scenes. [PUB] [CODE]
• CA-I2P: Channel-Adaptive Registration Network with Global Optimal Selection. [PUB] [pc.]
• CoMatch: Dynamic Covisibility-Aware Transformer for Bilateral Subpixel-Level Semi-Dense Image Matching. [PUB] [CODE]
• Correspondence-Free Fast and Robust Spherical Point Pattern Registration. [PUB] [CODE]
• Diff2I2P: Differentiable Image-to-Point Cloud Registration with Diffusion Prior. [PUB] [CODE]
• EDFFDNet: Towards Accurate and Efficient Unsupervised Multi-Grid Image Registration. [PUB]
• EMatch: A Unified Framework for Event-Based Optical Flow and Stereo Matching. [PUB] [CODE] [oth.]
• ERNet: Efficient Non-Rigid Registration Network for Point Sequences. [PUB]
• Fine-Grained 3D Gaussian Head Avatars Modeling from Static Captures Via Joint Reconstruction and Registration. [PUB]
• Flow4Agent: Long-form Video Understanding via Motion Prior from Optical Flow. [PUB]
• FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases. [PUB]
• GaussianReg: Rapid 2D/3D Registration for Emergency Surgery Via Explicit 3D Modeling with Gaussian Primitives. [PUB]
• HOMO-Feature: Cross-Arbitrary-Modal Image Matching with Homomorphism of Organized Major Orientation. [PUB] [oth.]
• How Do Optical Flow and Textual Prompts Collaborate to Assist in Audio-Visual Semantic Segmentation?. [PUB]
• HyperGCT: A Dynamic Hyper-GNN-Learned Geometric Constraint for 3D Registration. [PUB]
• LBM: Latent Bridge Matching for Fast Image-to-Image Translation. [PUB]
• Learning Dense Feature Matching via Lifting Single 2D Image to 3D Space. [PUB] [CODE]
• Learning Large Motion Estimation from Intermediate Representations with a High-Resolution Optical Flow Dataset Featuring Long-Range Dynamic Motion. [PUB]
• Leveraging Local Patch Alignment to Seam-Cutting for Large Parallax Image Stitching. [PUB] [CODE] [oth.]
• LLM-Enhanced Action-Aware Multi-Modal Prompt Tuning for Image-Text Matching. [PUB] [CODE]
• MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation. [PUB] [CODE]
• Mind the Gap: Aligning Vision Foundation Models to Image Feature Matching. [PUB]
• PixelStitch: Structure-Preserving Pixel-Wise Bidirectional Warps for Unsupervised Image Stitching. [PUB] [oth.]
• PriOr-Flow: Enhancing Primitive Panoramic Optical Flow with Orthogonal View. [PUB] [CODE]
• RARE: Refine Any Registration of Pairwise Point Clouds via Zero-Shot Learning. [PUB] [CODE]
• RegGS: Unposed Sparse Views Gaussian Splatting with 3DGS Registration. [PUB]
• Registration beyond Points: General Affine Subspace Alignment via Geodesic Distance on Grassmann Manifold. [PUB] [CODE]
• Removing Cost Volumes from Optical Flow Estimators. [PUB] [oth.]
• ReTracker: Exploring Image Matching for Robust Online Any Point Tracking. [PUB] [oth.]
• Towards Open-World Generation of Stereo Images and Unsupervised Matching. [PUB] [oth.]
• Turboreg: Turboclique for Robust and Efficient Point Cloud Registration. [PUB]
• U-ViLAR: Uncertainty-Aware Visual Localization for Autonomous Driving via Differentiable Association and Registration. [PUB] [rs.]
• Unsupervised Joint Learning of Optical Flow and Intensity with Event Cameras. [PUB] [CODE]
• Unsupervised Rgb-D Point Cloud Registration for Scenes With Low Overlap and Photometric Inconsistency. [PUB] [pc.]
• ZeroStereo: Zero-Shot Ste