SparseGF: A Height-Aware Sparse Segmentation Framework with Context Compression for Robust Ground Filtering Across Urban to Natural Scenes

• URL: http://arxiv.org/abs/2604.21356v1
• Date: Thu, 23 Apr 2026 07:15:12 GMT
• Title: SparseGF: A Height-Aware Sparse Segmentation Framework with Context Compression for Robust Ground Filtering Across Urban to Natural Scenes
• Abstract summary: SparseGF is a height-aware sparse segmentation framework enhanced with context compression.<n>It achieves leading performance in complex urban scenes, competitive results on mixed terrains, and moderate yet non-catastrophic accuracy in densely forested steep areas.
• Score: 13.187925022445434
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: High-quality digital terrain models derived from airborne laser scanning (ALS) data are essential for a wide range of geospatial analyses, and their generation typically relies on robust ground filtering (GF) to separate point clouds across diverse landscapes into ground and non-ground parts. Although current deep-learning-based GF methods have demonstrated impressive performance, especially in specific challenging terrains, their cross-scene generalization remains limited by two persistent issues: the context-detail dilemma in large-scale processing due to limited computational resources, and the random misclassification of tall objects arising from classification-only optimization. To overcome these limitations, we propose SparseGF, a height-aware sparse segmentation framework enhanced with context compression. It is built upon three key innovations: (1) a convex-mirror-inspired context compression module that condenses expansive contexts into compact representations while preserving central details; (2) a hybrid sparse voxel-point network architecture that effectively interprets compressed representations while mitigating compression-induced geometric distortion; and (3) a height-aware loss function that explicitly enforces topographic elevation priors during training to suppress random misclassification of tall objects. Extensive evaluations on two large-scale ALS benchmark datasets demonstrate that SparseGF delivers robust GF across urban to natural terrains, achieving leading performance in complex urban scenes, competitive results on mixed terrains, and moderate yet non-catastrophic accuracy in densely forested steep areas. This work offers new insights into deep-learning-based GF research and encourages further exploration toward truly cross-scene generalization for large-scale environmental monitoring.

Related papers

• NG-GS: NeRF-Guided 3D Gaussian Splatting Segmentation [65.34304674634713]
  We introduce NG-GS, a framework for high-quality object segmentation in 3DGS that explicitly addresses boundary discretization.<n>We show that our method achieves photorealistic state-of-the-art performance, with significant gains in boundary mIoU.
  arXiv  Detail & Related papers  (2026-04-16T07:14:07Z)
• Gaussian Belief Propagation Network for Depth Completion [38.053489092019824]
  Deep learning methods have achieved state-of-the-art (SOTA) performance, but handling the sparse and irregular nature of input depth data is a significant challenge.<n>We introduce the Gaussian Belief Propagation Network (GBPN), a novel framework integrating deep learning with probabilistic graphical models for end-to-end depth completion.<n>Extensive experiments demonstrate that GBPN achieves SOTA performance on the NYUv2 and KITTI benchmarks.
  arXiv  Detail & Related papers  (2026-01-29T05:44:41Z)
• GauSSmart: Enhanced 3D Reconstruction through 2D Foundation Models and Geometric Filtering [50.675710727721786]
  We propose GauSSmart, a hybrid method that bridges 2D foundational models and 3D Gaussian Splatting reconstruction.<n>Our approach integrates established 2D computer vision techniques, including convex filtering and semantic feature supervision.<n>We validate our approach across three datasets, where GauSSmart consistently outperforms existing Gaussian Splatting.
  arXiv  Detail & Related papers  (2025-10-16T03:38:26Z)
• D$^2$GS: Depth-and-Density Guided Gaussian Splatting for Stable and Accurate Sparse-View Reconstruction [73.61056394880733]
  3D Gaussian Splatting (3DGS) enables real-time, high-fidelity novel view synthesis (NVS) with explicit 3D representations.<n>We identify two key failure modes under sparse-view conditions: overfitting in regions with excessive Gaussian density near the camera, and underfitting in distant areas with insufficient Gaussian coverage.<n>We propose a unified framework D$2$GS, comprising two key components: a Depth-and-Density Guided Dropout strategy, and a Distance-Aware Fidelity Enhancement module.
  arXiv  Detail & Related papers  (2025-10-09T17:59:49Z)
• LC-SLab -- An Object-based Deep Learning Framework for Large-scale Land Cover Classification from Satellite Imagery and Sparse In-situ Labels [25.42215602005236]
  We propose LC-SLab, a framework for exploring object-based deep learning methods for large-scale land cover classification under sparse supervision.<n> LC-SLab supports both input-level aggregation via graph neural networks, and output-level aggregation by postprocessing results.<n>Our results show that object-based methods can match or exceed the accuracy of common pixel-wise models while producing substantially more coherent maps.
  arXiv  Detail & Related papers  (2025-09-19T11:08:24Z)
• Learning Fine-Grained Geometry for Sparse-View Splatting via Cascade Depth Loss [15.425094458647933]
  We introduce Hierarchical Depth-Guided Splatting (HDGS), a depth supervision framework that progressively refines geometry from coarse to fine levels.<n>By enforcing multi-scale depth consistency, our method substantially improves structural fidelity in sparse-view scenarios.
  arXiv  Detail & Related papers  (2025-05-28T12:16:42Z)
• Intern-GS: Vision Model Guided Sparse-View 3D Gaussian Splatting [95.61137026932062]
  Intern-GS is a novel approach to enhance the process of sparse-view Gaussian splatting.<n>We show that Intern-GS achieves state-of-the-art rendering quality across diverse datasets.
  arXiv  Detail & Related papers  (2025-05-27T05:17:49Z)
• Topology-Aware 3D Gaussian Splatting: Leveraging Persistent Homology for Optimized Structural Integrity [3.792470553976718]
  This work introduces Topology-Aware 3D Gaussian Splatting (Topology-GS)<n>Topology-GS addresses compromised pixel-level structural integrity due to incomplete initial geometric coverage.<n>Experiments on three novel-view benchmarks demonstrate that Topology-GS outperforms existing methods in terms of PSNR, SSIM, and LPIPS metrics.
  arXiv  Detail & Related papers  (2024-12-21T13:25:03Z)
• Decoupling Fine Detail and Global Geometry for Compressed Depth Map Super-Resolution [55.9977636042469]
  We propose a novel framework, termed geometry-decoupled network (GDNet), for compressed depth map super-resolution.<n>It decouples the high-quality depth map reconstruction process by handling global and detailed geometric features separately.<n>Our solution significantly outperforms current methods in terms of geometric consistency and detail recovery.
  arXiv  Detail & Related papers  (2024-11-05T16:37:30Z)
• CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes [53.107474952492396]
  CityGaussianV2 is a novel approach for large-scale scene reconstruction.<n>We implement a decomposed-gradient-based densification and depth regression technique to eliminate blurry artifacts and accelerate convergence.<n>Our method strikes a promising balance between visual quality, geometric accuracy, as well as storage and training costs.
  arXiv  Detail & Related papers  (2024-11-01T17:59:31Z)
• LMSeg: An end-to-end geometric message-passing network on barycentric dual graphs for large-scale landscape mesh segmentation [5.698076346359676]
  We introduce the BudjBim Wall dataset, a large-scale annotated mesh dataset from the UNESCO World Heritage-listed Budj Bim cultural landscape in Victoria, Australia.<n>We propose LMSeg, a deep graph message-passing network for semantic segmentation of large-scale meshes.<n>Experiments on three large-scale benchmarks (SUM, H3D, and BBW) show that LMSeg achieves 75.1% mIoU on SUM, 78.4% O.A. on H3D, and 62.4% mIoU on BBW, using only 2.4M lightweight parameters.
  arXiv  Detail & Related papers  (2024-07-05T07:55:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.