cs.CVNov 12, 2026

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

Authors: Ugo Insalaco, Jean-Emmanuel Deschaud, Pierre Dellenbach

Organizations: Mines Paris, PSL University Centre for robotics (CAOR) 75006 Paris, France · ChapsVision 4 Rue du Port aux Vins, 92150 Suresnes, France

Abstract

Cameras and LiDARs (Light Detection and Ranging) provide complementary observations of the same scene: cameras capture rich appearance cues while LiDAR sensors provide accurate geometric measurements. In this work, we address the problem of fine image-to-point cloud registration from a single image and a roughly estimated camera pose. On robotic platforms, residual reprojection errors of several pixels are commonly observed even after calibration due to temporal desynchronization, mechanical vibrations, or inaccuracies in point cloud reconstruction. Such errors can lead to decimeter-level geometric discrepancies at moderate distances and significantly affect multiple downstream tasks, such as dense cross-modal supervision, texture mapping, and semantic label transfer. To address this challenge, we introduce ReFineR: an offline framework to finely register individual images to pre-reconstructed point clouds. ReFineR builds upon differentiable point splatting rasterization and a smooth Gradient Orientation Measure (GOM) to iteratively refine the camera pose through analysis-by-synthesis optimization. We evaluated the method on a curated dataset of manually calibrated images collected from heterogeneous data sources. Furthermore, we show that an automatic point cloud rescale factor can be estimated prior to optimization, enabling robust refinement across a wide range of scenarios using a single scale-invariant formulation. The project page can be found at https://refiner-project.github.io/

Figures & tables

Appendix figures & tables18 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Image-to-Point Cloud Registration Made Easy with Rectified Flow-based LiDAR Upsampling

    Jul 16, 2026Reon Tabata, Kenji Koide, Shuji Oishi +4Camera-LiDAR FusionPoint Cloud Registration

  2. ZIL: Zero-shot Image-to-LiDAR Registration

    Sep 19, 2026Zijun Li, Xiaotian Sun, Xuelun Shen +6Cross-Modal Image RegistrationCamera-LiDAR Fusion