Skip to content
Preprint

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

Nov 2026 · 0 citations · 54 references
Computer Science

TL;DR

A point cloud super-resolution method based on multi-scale spatial priors and joint local-global modeling, which comprises a spatially gated fusion module, a multi-granularity local-global cooperative perception module, and 2D median-residual denoising is proposed.

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.

View source

Similar papers

Open access Oct 2026

OSPIR-DETR: Object-Selective Proxy Interaction and Gain-Guided Scale Alignment for Remote Sensing Object Detection

Remote sensing imagery is characterized by complex backgrounds, substantial scale variation, and numerous small targets, placing greater demands on semantic modeling of high-spatial-resolution features and feature integration across multiple scales. Within the D-FINE hybrid encoder, however, the relatively high-spatial...

Gao-Shan Song, Kan Chen, Guo-Qiang Chu et al. · 0 citations
Book Open access Nov 2026

IMPEL: Can Pretrained Image Diffusion Enable Realistic LiDAR Point Cloud Generation?

LiDAR data generation holds considerable potential for scalable 3D scene perception in autonomous systems. Existing works typically adapt image-domain generative architectures and train from scratch, but the lack of comparable-scale LiDAR data bottlenecks their accuracy in modeling 3D geometric details. The notable sem...

Han-Zhe Li, Da-Zhong Shen, Qiang Zhou et al. · 0 citations
Open access Sep 2026

A Frequency-Spatial Segmentation Network for High-Resolution Remote Sensing Images

The feature mapping stage is reconstructed to incorporate physical edge priors and frequency-domain attention-based denoising, and a Spatial Attention Wavelet Transform Feature Decomposer (SA-WTFD) is introduced in the frequency branch to adaptively suppress high-frequency background clutter and enhance discriminative...

Qi-Yuan Zhang, Jian-Shun Liu · 1 citation
Open access Oct 2026

A Parameter-Compact Network with Hierarchical Detail Enhancement and High-Resolution Multiscale Fusion for Small Object Detection in UAV Imagery

It is demonstrated that coordinated structural enhancement, high-resolution multiscale fusion, and adaptive prediction can improve UAV small-object detection with a compact parameter footprint.

Jia-Qi Li, Qing-Hua Zeng, Zhi Xiong et al. · 0 citations
Open access Oct 2026

Spatially variant neural blind deconvolution to reconstruct ground-based solar observations

High-resolution ground-based solar observations provide access to the smallest spatial scales in the lower solar atmosphere. However, Earth's turbulent atmosphere imposes a significant limitation, by reducing the spatial resolution of such observations. To obtain high-quality observations, post facto reconstruction tec...

C. Schirninger, R. Jarolim, A. Veronig et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.