cs.CVNov 3, 2026

SparseGraph-I2P: Consistency-Guided Hypothesis Selection for Efficient Image-to-Point-Cloud Registration

Authors: Ziyang Yu, Xiang Li, Qiong Chang, Jun Miyazaki

Organizations: School of Computing, Institute of Science Tokyo · School of Electronic Science & Engineering, Nanjing University

Abstract

Coarse-to-fine image-to-point-cloud (I2P) registration risks discarding correct but ambiguous patch pairs, while retaining more candidates repeats fine matching over overlapping patches. SparseGraph-I2P aims to improve registration recall by increasing the inlier ratio at the pose solver, using sensor or monocular depth. A Coarse Hypothesis Graph combines appearance with depth-derived first- and second-order compatibility to select a fixed budget of patch pairs. Sparse Fine Matching decodes each queried pixel once and skips pixel--point comparisons covered by an ancestor patch paired with the same point-cloud region. With sensor depth, depth-aware filtering ranks correspondences by SC2 spectral support for a single EPnP solve. With monocular depth, depth or inverse depth is calibrated from correspondence geometry before filtering. SparseGraph-I2P achieves the highest registration recall and lowest latency among the compared methods on RGB-D Scenes V2 and 7-Scenes with sensor depth. With predicted depth, it retains the highest recall on RGB-D Scenes V2 at an additional calibration cost. Code will be released.

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Hg-I2P: Bridging Modalities for Generalizable Image-to-Point-Cloud Registration via Heterogeneous Graphs

    Mar 30, 2026Pei An, Junfeng Ding, Jiaqi Yang +32D-3D Image RegistrationPoint Cloud Registration

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

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

  3. ReFineR: Single image to dense point cloud registration at pixel level with point splatting

    Nov 12, 2026Ugo Insalaco, Jean-Emmanuel Deschaud, Pierre DellenbachPoint Cloud RegistrationCross-Modal Image Registration