SBP-Net: Learning Thin Structure Reconstruction with Sliding-Box Projections

• URL: http://arxiv.org/abs/2606.04251v1
• Date: Tue, 02 Jun 2026 21:59:22 GMT
• Title: SBP-Net: Learning Thin Structure Reconstruction with Sliding-Box Projections
• Abstract summary: Reconstructing thin 3D structures is challenging due to their sparsity, scale variation, and complex geometry.<n>We propose a reconstruction approach based on local depth projections, which provide an efficient and informative 2D representation of thin structures.
• Score: 1.8907108368038215
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reconstructing thin 3D structures is challenging due to their sparsity, scale variation, and complex geometry. Such structures arise in a wide range of domains, including medical imaging of vascular systems and industrial pipe systems. While recent neural methods perform well on dense surfaces, they often fail to recover fine thin geometries. We propose a reconstruction approach based on local depth projections, which provide an efficient and informative 2D representation of thin structures. Specifically, we traverse the 3D model with a sliding box to generate local orthographic depth projections, which are processed by a neural network to reconstruct missing thin structures in 2D. The local reconstructions are subsequently fused back into the 3D model to produce a coherent and detailed shape. Experiments on pulmonary artery reconstruction from CT volumes and industrial pipeline recovery from synthetic and real scans demonstrate improved preservation of fine structural details over existing methods.

Related papers

• The Turning Point of 3D Plant Phenotyping: 3D Foundation Models Enable Minute-to-Second Cross-Crop Reconstruction and Beyond [24.45425568959962]
  We present one of the first cross-crop 3D phenotyping frameworks powered by 3DFMs.<n>We show that 3D Foundation Models reduce the average reconstruction time from 6.52 minutes to 1.58 seconds.
  arXiv  Detail & Related papers  (2026-07-02T06:10:54Z)
• Pano3D: Unified 3D Reconstruction and Panoptic Segmentation [68.18993232814061]
  We introduce an approach that performs 3D reconstruction and 3D panoptic segmentation in a unified framework.<n>We build on existing 3D reconstruction models and augment them with a set-based mask decoder.<n>Our method achieves state-of-the-art performance in 3D panoptic segmentation across ScanNet, ScanNet200, and ScanNet++ datasets.
  arXiv  Detail & Related papers  (2026-06-12T09:43:13Z)
• SPIDER: Structure-Preferential Implicit Deep Network for Biplanar X-ray Reconstruction [30.432335038130866]
  SPIDER is a supervised framework designed to reconstruct CT volumes from biplanar X-ray images.<n>It embeds anatomical constraints into the reconstruction process, thereby enhancing structural continuity and reducing soft-tissue artifacts.<n>Our approach demonstrates strong potential in downstream segmentation tasks, underscoring its utility in personalized treatment planning and image-guided surgical navigation.
  arXiv  Detail & Related papers  (2025-07-07T06:06:28Z)
• CrossSDF: 3D Reconstruction of Thin Structures From Cross-Sections [23.35977941611922]
  CrossSDF is a novel approach for extracting a 3D signed distance field from 2D signed distances generated from planar contours.<n>Our results demonstrate a significant improvement over existing methods, effectively reconstructing thin structures and producing accurate 3D models.
  arXiv  Detail & Related papers  (2024-12-05T12:38:18Z)
• Neural Image Unfolding: Flattening Sparse Anatomical Structures using Neural Fields [6.5082099033254135]
  Tomographic imaging reveals internal structures of 3D objects and is crucial for medical diagnoses.<n>Various organ-specific unfolding techniques exist to map their densely sampled 3D surfaces to a distortion-minimized 2D representation.<n>We deploy a neural field to fit the transformation of the anatomy of interest to a 2D overview image.
  arXiv  Detail & Related papers  (2024-11-27T14:58:49Z)
• AniSDF: Fused-Granularity Neural Surfaces with Anisotropic Encoding for High-Fidelity 3D Reconstruction [55.69271635843385]
  We present AniSDF, a novel approach that learns fused-granularity neural surfaces with physics-based encoding for high-fidelity 3D reconstruction.<n>Our method boosts the quality of SDF-based methods by a great scale in both geometry reconstruction and novel-view synthesis.
  arXiv  Detail & Related papers  (2024-10-02T03:10:38Z)
• Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshes [52.038346313823524]
  This paper introduces a novel framework called DTNet for 3D mesh reconstruction and generation via Disentangled Topology. Our method is able to produce high-quality meshes, particularly with diverse topologies, as compared with the state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-06-10T08:32:57Z)
• 3D Reconstruction of Curvilinear Structures with Stereo Matching DeepConvolutional Neural Networks [52.710012864395246]
  We propose a fully automated pipeline for both detection and matching of curvilinear structures in stereo pairs. We mainly focus on 3D reconstruction of dislocations from stereo pairs of TEM images.
  arXiv  Detail & Related papers  (2021-10-14T23:05:47Z)
• Vid2Curve: Simultaneous Camera Motion Estimation and Thin Structure Reconstruction from an RGB Video [90.93141123721713]
  Thin structures, such as wire-frame sculptures, fences, cables, power lines, and tree branches, are common in the real world. It is extremely challenging to acquire their 3D digital models using traditional image-based or depth-based reconstruction methods because thin structures often lack distinct point features and have severe self-occlusion. We propose the first approach that simultaneously estimates camera motion and reconstructs the geometry of complex 3D thin structures in high quality from a color video captured by a handheld camera.
  arXiv  Detail & Related papers  (2020-05-07T10:39:20Z)
• Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image [102.44347847154867]
  We propose a novel formulation that allows to jointly recover the geometry of a 3D object as a set of primitives. Our model recovers the higher level structural decomposition of various objects in the form of a binary tree of primitives. Our experiments on the ShapeNet and D-FAUST datasets demonstrate that considering the organization of parts indeed facilitates reasoning about 3D geometry.
  arXiv  Detail & Related papers  (2020-04-02T17:58:05Z)

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.