mlsanityData to 13 Oct 2026

SAR2Struct: Extracting 3D Semantic Structural Representation of Aircraft Targets from Single-View SAR Image

arXiv 2506.06757 ↗First posted 7 Jun 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

To translate synthetic aperture radar (SAR) image into interpretable forms for human understanding is the ultimate goal of SAR advanced information retrieval. Existing methods mainly focus on 3D surface reconstruction or local geometric feature extraction of targets, neglecting the role of structural modeling in capturing semantic information. This paper proposes a novel task: SAR target structure recovery, which aims to infer the components of a target and the structural relationships between its components, specifically symmetry and adjacency, from a single-view SAR image. Through learning the structural consistency and geometric diversity across the same type of targets as observed in different SAR images, it aims to derive the semantic representation of target directly from its 2D SAR image. To solve this challenging task, a two-step algorithmic framework based on structural descriptors is developed. Specifically, in the training phase, it first detects 2D keypoints from real SAR images, and then learns the mapping from these keypoints to 3D hierarchical structures using simulated data. During the testing phase, these two steps are integrated to infer the 3D structure from real SAR images. Experimental results validated the effectiveness of each step and demonstrated, for the first time, that 3D semantic structural representation of aircraft targets can be directly derived from a single-view SAR image.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 33 of its 60 references that are in the map. First posted on arXiv 7 Jun 2025.

Builds on

33 of 60 references.

References · 33

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,550
  2. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,889
  3. 2018End-to-End Multi-Task Learning with Attentioncited by 533
  4. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  5. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  6. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 206
  7. 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
  8. 2019CvxNet: Learnable Convex Decompositioncited by 174
  9. 2019Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboidscited by 124
  10. 2019PQ-NET: A Generative Part Seq2Seq Network for 3D Shapescited by 118
  11. 2019SDM-NET: Deep Generative Network for Structured Deformable Meshcited by 113
  12. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 103
21 more
  1. 2018Supervised Fitting of Geometric Primitives to 3D Point Cloudscited by 91
  2. 2019BAE-NET: Branched Autoencoder for Shape Co-Segmentationcited by 89
  3. 2020Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Imagecited by 72
  4. 2018Im2Struct: Recovering 3D Shape Structure from a Single RGB Imagecited by 55
  5. 2024Part123: Part-aware 3D Reconstruction from a Single-view Imagecited by 54
  6. 2019PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentationcited by 44
  7. 2021Unsupervised Learning for Cuboid Shape Abstraction via Joint Segmentation from Point Cloudscited by 44
  8. 2023PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervisioncited by 36
  9. 2020DSG-Net: Learning Disentangled Structure and Geometry for 3D Shape Generationcited by 31
  10. 2021Robust and Accurate Superquadric Recovery: a Probabilistic Approachcited by 29
  11. 2022RIM-Net: Recursive Implicit Fields for Unsupervised Learning of Hierarchical Shape Structurescited by 19
  12. 2023Marching-Primitives: Shape Abstraction from Signed Distance Functioncited by 19
  13. 2022ANISE: Assembly-based Neural Implicit Surface rEconstructioncited by 16
  14. 2023Iterative Superquadric Recomposition of 3D Objects from Multiple Viewscited by 13
  15. 2021Recognizing Vector Graphics without Rasterizationcited by 11
  16. 2024Quantifying Task Priority for Multi-Task Optimizationcited by 11
  17. 2022Semi-supervised 3D shape segmentation with multilevel consistency and part substitutioncited by 8
  18. 2023DAE-Net: Deforming Auto-Encoder for fine-grained shape co-segmentationcited by 7
  19. 2024DPA-Net: Structured 3D Abstraction from Sparse Views via Differentiable Primitive Assemblycited by 5
  20. 2022Differentiable SAR Renderer and SAR Target Reconstructioncited by 4
  21. 2023Polygon Intersection-over-Union Loss for Viewpoint-Agnostic Monocular 3D Vehicle Detectioncited by 1

Built on by

Not cited yet.