• Home
  • Search
  • Projection Kernel regularization for diffusion-based multimodal remote sensing segmentation.
  • https://doi.org/10.1038/s41598-026-44603-4Copy DOI Icon

Projection Kernel regularization for diffusion-based multimodal remote sensing segmentation.

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

With the increasing availability of multimodal remote sensing (RS) data, semantic segmentation that leverages complementary information from true orthophotos (TOP) and digital surface models (DSM) has become essential for urban analysis. Diffusion-based segmentation provides an effective iterative refinement mechanism for modeling complex multimodal distributions; however, conventional pixel-wise supervision emphasizes local accuracy while overlooking global distribution alignment, often leading to inconsistent predictions and blurred object boundaries. Although maximum mean discrepancy (MMD) measures global statistical differences between predicted and ground-truth distributions, its effectiveness in high-dimensional class-probability spaces is limited by directional cancellation effects that reduce sensitivity to complex distribution shifts. To address this issue, we propose a projection-kernel regularized diffusion-based multimodal RS segmentation framework that enforces global statistical alignment through distribution-level regularization rather than modifying the intrinsic diffusion process. The proposed regularization performs multi-directional projections of high-dimensional class-probability vectors onto one-dimensional subspaces and derives a closed-form kernel integration to avoid numerical sampling across projection directions, enabling efficient and stable global distribution matching. In addition, a Cross-Attention Dual-Encoder Fusion (CADEF) module is introduced to alleviate geometry-texture misalignment, and a Hierarchical EMA-Gated Recursive Denoising (HERD) mechanism is designed to stabilize multiscale feature refinement. Experiments on the ISPRS Vaihingen and Potsdam benchmarks demonstrate that the proposed regularization consistently improves segmentation accuracy over state-of-the-art CNN-, Transformer-, and diffusion-based baselines, yielding enhanced global consistency and sharper boundary delineation. Code is available at: https://github.com/tonyy127/PKDiff.

Similar Papers
  • Research Article
  • Citations1

MMFNet: A Mamba-Based Multimodal Fusion Network for Remote Sensing Image Semantic Segmentation.

  • Oct 08, 2025
  • Sensors (Basel, Switzerland)
  • Jingting Qiu +4
  • Book Chapter
  • Citations2

Attention-Based DSM Fusion Network for Semantic Segmentation of High-Resolution Remote-Sensing Images

  • Jan 01, 2021
  • Minfei Lu +5
  • Research Article
  • Citations31

Structure-Aware Weakly Supervised Network for Building Extraction From Remote Sensing Images

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Hui Chen +6
  • Research Article
  • Citations29

Hybrid Attention Fusion Embedded in Transformer for Remote Sensing Image Semantic Segmentation

  • Jan 01, 2024
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Yan Chen +8
  • Conference Article
  • Citations6

Semi-automatic true orthophoto production by using LIDAR data

  • Jan 01, 2007
  • A Gunay +2
  • PDF
  • Research Article
  • Citations7

Multi-Source Fusion Enhanced Feature Segmentation in Remote Sensing Imagery

  • Oct 18, 2024
  • ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
  • Siman Wang +1
  • Research Article

HL-SAM-Seg: Complementary High- and Low-Resolution Features Based on SAM for Remote Sensing Image Semantic Segmentation

  • Jan 01, 2026
  • IEEE Transactions on Geoscience and Remote Sensing
  • Siting Xiong +5
  • Research Article
  • Citations8

Frequency-Guided Denoising Network for Semantic Segmentation of Remote Sensing Images

  • Jan 01, 2026
  • IEEE Transactions on Geoscience and Remote Sensing
  • Xin Li +7
  • Research Article

AIG 2 AN: Ambiguous-Interpretation Generalized GAN for Self-Supervised Raster-Vector Semantic Segmentation for cross-modal Remote Sensing Image

  • Jan 01, 2026
  • IEEE Transactions on Geoscience and Remote Sensing
  • Chang Li +3
  • Research Article
  • Citations5

A Bias Correction Semi-Supervised Semantic Segmentation Framework for Remote Sensing Images

  • Jan 01, 2025
  • IEEE Transactions on Geoscience and Remote Sensing
  • Li Zhang +5
  • PDF
  • Research Article
  • Citations23

Attentively Learning Edge Distributions for Semantic Segmentation of Remote Sensing Imagery

  • Dec 26, 2021
  • Remote Sensing
  • Xin Li +4
  • PDF
  • Research Article
  • Citations6

CMR-net: A cross modality reconstruction network for multi-modality remote sensing classification.

  • Jun 25, 2024
  • PloS one
  • Huiqing Wang +2
  • Research Article
  • Citations12

A Novel Boundary Loss Function in Deep Convolutional Networks to Improve the Buildings Extraction From High-Resolution Remote Sensing Images

  • Jan 01, 2022
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Hamidreza Hosseinpour +2
  • PDF
  • Research Article

Evaluate the Impact of Class Granularity in Point Cloud Semantic Segmentation on DTM Accuracy

  • May 19, 2025
  • The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
  • Haval Abduljabbar Sadeq
  • Research Article

CW-SwinUNet: a novel semantic segmentation approach for very-high-resolution remote sensing imagery

  • Oct 23, 2025
  • International Journal of Remote Sensing
  • Zhanyuan Chang +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.