Joint Neural SDF Reconstruction and Semantic Segmentation for CAD Models

• URL: http://arxiv.org/abs/2510.03837v1
• Date: Sat, 04 Oct 2025 15:29:36 GMT
• Title: Joint Neural SDF Reconstruction and Semantic Segmentation for CAD Models
• Abstract summary: We propose a data-efficient pipeline that augments an implicit reconstruction network based on neural SDF parts with a part-segmentation head trained under PartField-generated supervision.<n>Unlike methods tied to fixed meshes, our model accepts meshes with any number of parts and produces coherent, geometry-aligned labels in a single pass.
• Score: 0.9668407688201358
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose a simple, data-efficient pipeline that augments an implicit reconstruction network based on neural SDF-based CAD parts with a part-segmentation head trained under PartField-generated supervision. Unlike methods tied to fixed taxonomies, our model accepts meshes with any number of parts and produces coherent, geometry-aligned labels in a single pass. We evaluate on randomly sampled CAD meshes from the ABC dataset with intentionally varied part cardinalities, including over-segmented shapes, and report strong performance across reconstruction (CDL1/CDL2, F1-micro, NC) and segmentation (mIoU, Accuracy), together with a new Segmentation Consistency metric that captures local label smoothness. We attach a lightweight segmentation head to the Flat-CAD SDF trunk; on a paired evaluation it does not alter reconstruction while providing accurate part labels for meshes with any number of parts. Even under degraded reconstructions on thin or intricate geometries, segmentation remains accurate and label-coherent, often preserving the correct part count. Our approach therefore offers a practical route to semantically structured CAD meshes without requiring curated taxonomies or exact palette matches. We discuss limitations in boundary precision, partly due to per-face supervision, and outline paths toward boundary-aware training and higher resolution labels.

Related papers

• SegDem: Segmentation helps Demosaicing [52.515779223891705]
  Image demosaicing reconstructs a full-color image from incomplete color measurements produced by a sensor covered with a color filter (CFA)<n>Most existing methods formulate demosaicing as pixel-level reconstruction.<n>SegDem is a cross-task decoder representation transfer framework for demosaicing.
  arXiv  Detail & Related papers  (2026-08-08T04:49:20Z)
• SCAPO: Self-Supervised Category-Level Articulated Pose Estimation from a Single 3D Observation [54.98864436812187]
  We propose a self-supervised framework that estimates canonical geometry, rigid part segmentation, and joint pivots, axes, and articulation states from a single RGB-D observation.<n> Experiments on synthetic and real articulated-object datasets show that our SCAPO recovers consistent part structure and accurate articulation parameters and outperforms all self-supervised baselines.
  arXiv  Detail & Related papers  (2026-06-01T09:04:49Z)
• Beyond Spatial Compression: Interface-Centric Generative States for Open-World 3D Structure [55.17771962316751]
  Current 3D tokenizers treat representation as spatial compression, but leave component ownership and attachment validity implicit.<n>We formulate an alternative view, interface-centric generative states, in which tokenization constructs an operational state rather than a passive compressed code.<n>We instantiate this formulation with Component-Conditioned Canonical Local Tokens (C2LT-3D), factorizing representation into canonical local geometry, partition-conditioned context, and relational seam variables.
  arXiv  Detail & Related papers  (2026-05-11T12:09:28Z)
• STEP-Parts: Geometric Partitioning of Boundary Representations for Large-Scale CAD Processing [0.8602553195689512]
  Many CAD learning pipelines discretize Boundary Representations (B-Reps) into triangle meshes, discarding analytic surface structure and topological adjacency.<n>We present STEP-Parts, a deterministic CAD-to-supervision toolchain that extracts geometric instance partitions directly from raw STEP B-Reps.<n>The pipeline processes approximately 180,000 models in under six hours on a consumer CPU.
  arXiv  Detail & Related papers  (2026-04-16T12:12:27Z)
• SepFormer: Coarse-to-fine Separator Regression Network for Table Structure Recognition [0.5120567378386615]
  We present SepFormer, which integrates the split-and-merge paradigm into a single step through separator regression with a DETR-style architecture.<n>SepFormer can run on average at 25.6 FPS while achieving comparable performance with state-of-the-art methods on several benchmark datasets.
  arXiv  Detail & Related papers  (2025-06-27T05:20:42Z)
• Detection Based Part-level Articulated Object Reconstruction from Single RGBD Image [52.11275397911693]
  We propose an end-to-end trainable, cross-category method for reconstructing multiple man-made articulated objects from a single RGBD image.<n>We depart from previous works that rely on learning instance-level latent space, focusing on man-made articulated objects with predefined part counts.<n>Our method successfully reconstructs variously structured multiple instances that previous works cannot handle, and outperforms prior works in shape reconstruction and kinematics estimation.
  arXiv  Detail & Related papers  (2025-04-04T05:08:04Z)
• Reconstruction of Contour Lines During the Digitization of Contour Maps to Build a Digital Elevation Model [0.0]
  broken contour segments impose a greater risk while building a Digital Elevation Model (DEM)<n>In this project, a simple yet efficient mechanism is used to match and reconnect the endpoints of the broken segments accurately and efficiently.<n>The purpose of this work is to reconnect the broken contour lines generated during the digitization of the contour map, to help build the most appropriate digital elevation model for the corresponding contour map.
  arXiv  Detail & Related papers  (2024-12-20T03:02:42Z)
• SLoRD: Structural Low-Rank Descriptors for Shape Consistency in Vertebrae Segmentation [12.964962611736443]
  Multi-class vertebrae segmentation from CT images is crucial for various clinical applications.<n>Existing single-stage and multi-stage methods suffer from imprecise vertebrae segmentation.<n>A contour generation network is proposed based on Structural Low-Rank Descriptors for shape consistency.
  arXiv  Detail & Related papers  (2024-07-11T14:39:54Z)
• Split-and-Fit: Learning B-Reps via Structure-Aware Voronoi Partitioning [50.684254969269546]
  We introduce a novel method for acquiring boundary representations (B-Reps) of 3D CAD models. We apply a spatial partitioning to derive a single primitive within each partition. We show that our network, coined NVD-Net for neural Voronoi diagrams, can effectively learn Voronoi partitions for CAD models from training data.
  arXiv  Detail & Related papers  (2024-06-07T21:07:49Z)
• PS-CAD: Local Geometry Guidance via Prompting and Selection for CAD Reconstruction [86.726941702182]
  We introduce geometric guidance into the reconstruction network PS-CAD. We provide the geometry of surfaces where the current reconstruction differs from the complete model as a point cloud. Second, we use geometric analysis to extract a set of planar prompts, that correspond to candidate surfaces.
  arXiv  Detail & Related papers  (2024-05-24T03:43:55Z)
• KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformation [87.23575166061413]
  KP-RED is a unified KeyPoint-driven REtrieval and Deformation framework.<n>It takes object scans as input and jointly retrieves and deforms the most geometrically similar CAD models.
  arXiv  Detail & Related papers  (2024-03-15T08:44:56Z)
• Dual-scale Enhanced and Cross-generative Consistency Learning for Semi-supervised Medical Image Segmentation [49.57907601086494]
  Medical image segmentation plays a crucial role in computer-aided diagnosis. We propose a novel Dual-scale Enhanced and Cross-generative consistency learning framework for semi-supervised medical image (DEC-Seg)
  arXiv  Detail & Related papers  (2023-12-26T12:56:31Z)
• Edge-aware Plug-and-play Scheme for Semantic Segmentation [4.297988192695948]
  The proposed method can be seamlessly integrated into any state-of-the-art (SOTA) models with zero modification. The experimental results indicate that the proposed method can be seamlessly integrated into any state-of-the-art (SOTA) models with zero modification.
  arXiv  Detail & Related papers  (2023-03-18T02:17:37Z)
• SOLD2: Self-supervised Occlusion-aware Line Description and Detection [95.8719432775724]
  We introduce the first joint detection and description of line segments in a single deep network. Our method does not require any annotated line labels and can therefore generalize to any dataset. We evaluate our approach against previous line detection and description methods on several multi-view datasets.
  arXiv  Detail & Related papers  (2021-04-07T19:27:17Z)
• Learning Fine-Grained Segmentation of 3D Shapes without Part Labels [29.837938445219528]
  Learning-based 3D shape segmentation is usually formulated as a semantic labeling problem, assuming that all parts of training shapes are annotated with a given set of tags. We propose deep clustering to learn part priors from a shape dataset with fine-grained segmentation but no part labels. Our method is evaluated with a challenging benchmark of fine-grained segmentation, showing state-of-the-art performance.
  arXiv  Detail & Related papers  (2021-03-24T07:27:07Z)
• Batch Coherence-Driven Network for Part-aware Person Re-Identification [79.33809815035127]
  Existing part-aware person re-identification methods typically employ two separate steps: namely, body part detection and part-level feature extraction. We propose NetworkBCDNet that bypasses body part during both the training and testing phases while still semantically aligned features.
  arXiv  Detail & Related papers  (2020-09-21T09:04:13Z)
• Learning to segment from misaligned and partial labels [0.0]
  Many non-urban settings lack the ground-truth needed for accurate segmentation. Open source infrastructure annotations like OpenStreetMaps (OSM) are representative of this issue. We present a novel and generalizable two-stage framework that enables improved pixel-wise image segmentation given misaligned and missing annotations.
  arXiv  Detail & Related papers  (2020-05-27T06:02:58Z)

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.