Targeted Structure Completion for Sparse-View 3D Reconstruction in Autonomous Driving

• URL: http://arxiv.org/abs/2607.04661v1
• Date: Mon, 06 Jul 2026 04:31:45 GMT
• Title: Targeted Structure Completion for Sparse-View 3D Reconstruction in Autonomous Driving
• Abstract summary: Reconstructing 3D scene structures from sparse, low-overlap observations is a fundamental challenge in autonomous driving.<n>We propose FocusGS, a framework that shifts the paradigm from global densification to targeted structural completion.<n>We show that FocusGS achieves a superior efficiency-quality trade-off, advancing state-of-the-art performance on driving-centric benchmarks.
• Score: 13.279942633870702
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reconstructing 3D scene structures from sparse, low-overlap observations remains a fundamental challenge in autonomous driving. Recent state-of-the-art frameworks achieve promising results by incorporating voxel-based Gaussians, but incur substantial computational redundancy due to a uniform volumetric processing strategy. To bridge the gap between the efficiency of pixel-based Gaussian methods and the structural completeness of voxel-based Gaussian approaches, we propose FocusGS, a simple yet effective framework that shifts the paradigm from global densification to targeted structural completion. Our central insight is that structural completion should be decoupled from deterministic regions, with computation concentrated exclusively on areas exhibiting geometric ambiguity. Specifically, FocusGS addresses the localization challenge by deriving a 3D Geometric Ambiguity Manifold to accurately isolate localized areas prone to occlusion and high geometric uncertainty. To overcome the subsequent manifold completion challenge, we design a lightweight targeted structure completion module that selectively instantiates and optimizes continuous Gaussian queries strictly within this unstructured, sparse topological subspace. Extensive experiments demonstrate that FocusGS achieves a superior efficiency-quality trade-off, advancing state-of-the-art performance on driving-centric benchmarks while naturally reducing the total number of Gaussians by ~74% and decreasing rendering time by ~34%.

Related papers

• SphereSOD: Geometry-Structure Coupled Learning for 360 Salient Object Detection [75.77856258186854]
  360 salient object detection aims to accurately segment salient regions across a full field of view.<n>Existing methods mainly focus on compensating projection distortion while overlooking the interaction between panoramic geometry and salient object structure.<n>We propose SphereSOD, an ERP-native framework that couples panoramic geometry with evolving salient structures.
  arXiv  Detail & Related papers  (2026-09-07T14:47:54Z)
• SPARE-GS: Structural Parsimony and Resource Efficiency for 3D Gaussian Splatting [70.5411715784827]
  3D Gaussian Splatting (3DGS) achieves high-fidelity novel view synthesis in real-time.<n>But its training efficiency and representation compactness are hindered by excessive primitive proliferation.<n>We propose SPARE-GS, a framework that dynamically aligns the distribution of 3D Gaussian primitives with regional representational demand.
  arXiv  Detail & Related papers  (2026-07-18T03:55:12Z)
• 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)
• RMGS-SLAM: Real-time Multi-sensor Gaussian Splatting SLAM [19.6725809458616]
  We present a tightly coupled LiDAR-Inertial-Visual 3DGS-based SLAM framework for real-time pose estimation and mapping.<n>The proposed method achieves a state of the art among real-time efficiency, localization accuracy, and rendering quality across diverse real-world scenes.
  arXiv  Detail & Related papers  (2026-04-14T16:36:11Z)
• Hierarchical Informative Path Planning via Graph Guidance and Trajectory Optimization [10.020847331719398]
  We study informative path planning (IPP) with travel budgets in cluttered environments, where an agent collects measurements of a latent field modeled as a Gaussian process (GP) to reduce uncertainty at target locations.<n>We propose a hierarchical framework with three stages: (i) graph-based global planning, (ii) segment-wise budget allocation using geometric and kernel bounds, and (iii) spline-based refinement of each segment with hard constraints and obstacle pruning.
  arXiv  Detail & Related papers  (2026-01-23T23:27:20Z)
• COSMOS: Coherent Supergaussian Modeling with Spatial Priors for Sparse-View 3D Splatting [2.549594916296063]
  3D Gaussian Splatting (3DGS) has recently emerged as a promising approach for 3D reconstruction.<n>We propose Coherent supergaussian Modeling with Spatial Priors (COSMOS) to address this issue.<n>Our experiments on Blender and DTU show that COSMOS surpasses state-of-the-art methods in sparse-view settings without any external depth supervision.
  arXiv  Detail & Related papers  (2025-12-17T04:55:15Z)
• SVRecon: Sparse Voxel Rasterization for Surface Reconstruction [60.92372415355283]
  We extend the recently proposed sparse voxelization paradigm to the task of high-fidelity surface reconstruction by integrating SVRecon.<n>Our method achieves strong reconstruction accuracy while having consistently speedy convergence.
  arXiv  Detail & Related papers  (2025-11-21T16:32:01Z)
• Multi-Sample Anti-Aliasing and Constrained Optimization for 3D Gaussian Splatting [6.336372495476242]
  We propose a comprehensive optimization framework integrating multisample anti-aliasing with dual geometric constraints.<n>Our system computes pixel colors through adaptive blending of quadruple subsamples, effectively reducing aliasing artifacts in high-frequency components.<n>Our method achieves state-of-the-art performance in detail preservation, particularly in preserving high-frequency textures and sharp discontinuities.
  arXiv  Detail & Related papers  (2025-08-14T10:14:36Z)
• MonoGSDF: Exploring Monocular Geometric Cues for Gaussian Splatting-Guided Implicit Surface Reconstruction [86.87464903285208]
  We introduce MonoGSDF, a novel method that couples primitives with a neural Signed Distance Field (SDF) for high-quality reconstruction.<n>To handle arbitrary-scale scenes, we propose a scaling strategy for robust generalization.<n>Experiments on real-world datasets outperforms prior methods while maintaining efficiency.
  arXiv  Detail & Related papers  (2024-11-25T20:07:07Z)
• MCGS: Multiview Consistency Enhancement for Sparse-View 3D Gaussian Radiance Fields [100.90743697473232]
  Radiance fields represented by 3D Gaussians excel at synthesizing novel views, offering both high training efficiency and fast rendering.<n>Existing methods often incorporate depth priors from dense estimation networks but overlook the inherent multi-view consistency in input images.<n>We propose a view synthesis framework based on 3D Gaussian Splatting, enabling scene reconstruction from sparse views.
  arXiv  Detail & Related papers  (2024-10-15T08:39:05Z)
• GaussianRoom: Improving 3D Gaussian Splatting with SDF Guidance and Monocular Cues for Indoor Scene Reconstruction [5.112375652774415]
  We propose a unified optimization framework that integrates neural signed distance fields (SDFs) with 3DGS for accurate geometry reconstruction and real-time rendering.<n>Our method achieves state-of-the-art performance in both surface reconstruction and novel view synthesis.
  arXiv  Detail & Related papers  (2024-05-30T03:46:59Z)
• PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection [57.49788100647103]
  LiDAR-based 3D object detection is an important task for autonomous driving. Current approaches suffer from sparse and partial point clouds of distant and occluded objects. In this paper, we propose a novel two-stage approach, namely PC-RGNN, dealing with such challenges by two specific solutions.
  arXiv  Detail & Related papers  (2020-12-18T18:06:43Z)

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.