mlsanityData to 7 Oct 2026

FS-I2P:A Hierarchical Focus-Sweep Registration Network with Dynamically Allocated Depth

arXiv 2605.07607 ↗First posted 8 May 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Image-to-point cloud registration is often challenged by viewpoint changes, cross-modal discrepancies, and repetitive textures, which induce scale ambiguity and consequently lead to erroneous correspondences. Recent detection-free methods alleviate this issue by leveraging multi-scale features and transformer-based interactions. However, they still suffer from attention drift across layers and intra-scale inconsistencies, hindering precise registration. Inspired by human behavior, we propose a ``Focus--Sweep'' paradigm and develop a Hierarchical Focus--Sweep Interaction Module within an SSM-based framework to enhance multi-level cross-modal feature association. In addition, we introduce a Dynamic Layer Allocation Strategy that adaptively determines the iteration depth to better exploit geometric constraints and improve matching robustness. Extensive experiments and ablations on two benchmarks, RGB-D Scenes V2 and 7-Scenes, demonstrate that our approach achieves state-of-the-art performance.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 51 of its 91 references that are in the map. First posted on arXiv 8 May 2026.

Builds on

51 of 91 references.

References · 51

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  6. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  7. 2016Improved Techniques for Training GANscited by 2,938
  8. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  9. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  10. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  11. 2024VMamba: Visual State Space Modelcited by 955
  12. 2020Circle Loss: A Unified Perspective of Pair Similarity Optimizationcited by 402
38 more
  1. 2020PREDATOR: Registration of 3D Point Clouds with Low Overlapcited by 287
  2. 2016DSAC - Differentiable RANSAC for Camera Localizationcited by 264
  3. 2017Hand Keypoint Detection in Single Images using Multiview Bootstrappingcited by 231
  4. 2022Geometric Transformer for Fast and Robust Point Cloud Registrationcited by 200
  5. 2021CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registrationcited by 151
  6. 2024Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speedcited by 119
  7. 2019Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filterscited by 117
  8. 2019Hierarchical Scene Coordinate Classification and Regression for Visual Localizationcited by 93
  9. 2023GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformercited by 83
  10. 20192D3D-MatchNet: Learning to Match Keypoints Across 2D Image and 3D Point Cloudcited by 62
  11. 2021DeepI2P: Image-to-Point Cloud Registration via Deep Classificationcited by 58
  12. 2017Semantic Visual Localizationcited by 54
  13. 2022Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspectivecited by 46
  14. 2021Style-based Point Generator with Adversarial Rendering for Point Cloud Completioncited by 45
  15. 2022CorrI2P: Deep Image-to-Point Cloud Registration via Dense Correspondencecited by 43
  16. 2021P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matchingcited by 42
  17. 2023FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimatorscited by 29
  18. 20232D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Cloudscited by 27
  19. 2017Robust Visual SLAM with Point and Line Featurescited by 23
  20. 2021Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Criticcited by 23
  21. 2023SE-ORNet: Self-Ensembling Orientation-aware Network for Unsupervised Point Cloud Shape Correspondencecited by 19
  22. 2024EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splattingcited by 15
  23. 2025Bridge 2D-3D: Uncertainty-aware Hierarchical Registration Network with Domain Alignmentcited by 14
  24. 2025Brightness Perceiving for Recursive Low-Light Image Enhancementcited by 14
  25. 2022Efficient Exploration in Resource-Restricted Reinforcement Learningcited by 10
  26. 2025CA-I2P: Channel-Adaptive Registration Network with Global Optimal Selectioncited by 8
  27. 2025Diff2I2P: Differentiable Image-to-Point Cloud Registration with Diffusion Priorcited by 8
  28. 2024Unsupervised Template-assisted Point Cloud Shape Correspondence Networkcited by 7
  29. 2023Not Every Side Is Equal: Localization Uncertainty Estimation for Semi-Supervised 3D Object Detectioncited by 6
  30. 2025Adaptive Agent Selection and Interaction Network for Image-to-point cloud Registrationcited by 6
  31. 2025State Space Model Meets Transformer: A New Paradigm for 3D Object Detectioncited by 5
  32. 2023Quantity-Aware Coarse-to-Fine Correspondence for Image-to-Point Cloud Registrationcited by 4
  33. 2025EdgeRegNet: Edge Feature-based Multimodal Registration Network between Images and LiDAR Point Cloudscited by 3
  34. 2025StruMamba3D: Exploring Structural Mamba for Self-supervised Point Cloud Representation Learningcited by 3
  35. 2025SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image Segmentationcited by 3
  36. 2025Advanced Object Detection and Pose Estimation with Hybrid Task Cascade and High-Resolution Networkscited by 2
  37. 2025Exploring Semantic Masked Autoencoder for Self-supervised Point Cloud Understandingcited by 1
  38. 2026GeoGuide: Hierarchical Geometric Guidance for Open-Vocabulary 3D Semantic Segmentationcited by 1

50 most cited of 51 All 51 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching
  2. 2026Towards Zero-Shot Point Cloud Registration Across Diverse Scales, Scenes, and Sensor Setups
  3. 2023DIPR: Efficient Point Cloud Registration via Dynamic Iteration
  4. 2026DPA-I2P: Depth-Guided Projective Alignment for Image-to-Point-Cloud Registration in Autonomous Driving
  5. 2025RARE: Refine Any Registration of Pairwise Point Clouds via Zero-Shot Learning
  6. 2024SRIF: Semantic Shape Registration Empowered by Diffusion-based Image Morphing and Flow Estimation
  7. 2026CRFT: Consistent-Recurrent Feature Flow Transformer for Cross-Modal Image Registration
  8. 2026Image-to-Point Cloud Registration Made Easy with Rectified Flow-based LiDAR Upsampling