cs.CVNov 2, 2026

Local-Global Joint Modeling for Point Cloud Super-Resolution Guided by Multi-Scale Spatial Priors

Authors: Wang Yang, Wenyi Ge

Organizations: College of Computer Science, Chengdu University of Information Technology, Chengdu 610225, China

Abstract

Range-image-based point cloud super-resolution provides an effective way to reconstruct sparse outdoor point clouds by projecting low-resolution LiDAR scans into a regular 2D representation. However, current methods still face three challenges. First, range images exhibit pronounced vertical nonuniformity, with sparse observations in distant regions and denser observations in nearby regions. Some cross-scale fusion mechanisms do not account for the varying reliability of features at different vertical positions, allowing invalid values and noise from distant sparse regions to propagate into the decoder. Second, a single convolutional or sequence-modeling architecture often struggles to preserve both local high-frequency geometric details and global long-range dependencies, resulting in over-smoothed reconstructions. Third, smooth transition depths near foreground-background boundaries can produce spike artifacts when the 2D range image is back-projected into 3D. To address these issues, we propose a point cloud super-resolution method based on multi-scale spatial priors and joint local-global modeling. The design comprises a spatially gated fusion module, a multi-granularity local-global cooperative perception module, and 2D median-residual denoising. Experiments on KITTI-360 and nuScenes demonstrate effective reconstruction, with IoU scores of 0.4703 and 0.3593, respectively, supporting the feasibility of the proposed method for range-image super-resolution.

Figures & tables

Explore similar work

CardsList
  1. Fast and Accurate Outlier-Aware LiDAR Super-Resolution for SLAM Applications

    Jun 26, 2026Christos Anagnostopoulos, Alexandros Gkillas, Nikos Piperigkos +1Simultaneous Localization and MappingDeep Unfolding

  2. 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