mlsanityData to 7 Oct 2026

DualPrim: Compact 3D Reconstruction with Positive and Negative Primitives

arXiv 2603.16133 ↗First posted 17 Mar 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Neural reconstructions often trade structure for fidelity, yielding dense and unstructured meshes with irregular topology and weak part boundaries that hinder editing, animation, and downstream asset reuse. We present DualPrim, a compact and structured 3D reconstruction framework. Unlike additive-only implicit or primitive methods, DualPrim represents shapes with positive and negative superquadrics: the former builds the bases while the latter carves local volumes through a differentiable operator, enabling topology-aware modeling of holes and concavities. This additive-subtractive design increases the representational power without sacrificing compactness or differentiability. We embed DualPrim in a volumetric differentiable renderer, enabling end-to-end learning from multi-view images and seamless mesh export via closed-form boolean difference. Empirically, DualPrim delivers state-of-the-art accuracy and produces compact, structured, and interpretable outputs that better satisfy downstream needs than additive-only alternatives.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 51 of its 68 references that are in the map. First posted on arXiv 17 Mar 2026.

Builds on

51 of 68 references.

References · 51

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  2. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  3. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  4. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  5. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,144
  6. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
  7. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  8. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 661
  9. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  10. 2021Extracting Triangular 3D Models, Materials, and Lighting From Imagescited by 363
  11. 2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 311
  12. 2023FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularizationcited by 310
38 more
  1. 2023Text-to-3D using Gaussian Splattingcited by 299
  2. 2020PolyGen: An Autoregressive Generative Model of 3D Meshescited by 267
  3. 2023MeshGPT: Generating Triangle Meshes with Decoder-Only Transformerscited by 254
  4. 2024A Survey on 3D Gaussian Splattingcited by 221
  5. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  6. 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
  7. 2024StableNormal: Reducing Diffusion Variance for Stable and Sharp Normalcited by 153
  8. 2018Scan2CAD: Learning CAD Model Alignment in RGB-D Scanscited by 142
  9. 2024MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformerscited by 140
  10. 2023Flexible Isosurface Extraction for Gradient-Based Mesh Optimizationcited by 138
  11. 2019Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboidscited by 123
  12. 2022HF-NeuS: Improved Surface Reconstruction Using High-Frequency Detailscited by 120
  13. 2017CSGNet: Neural Shape Parser for Constructive Solid Geometrycited by 106
  14. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 101
  15. 2023RobustNeRF: Ignoring Distractors with Robust Lossescited by 101
  16. 2019Learning elementary structures for 3D shape generation and matchingcited by 98
  17. 2020UCSG-Net -- Unsupervised Discovering of Constructive Solid Geometry Treecited by 77
  18. 2021ROCA: Robust CAD Model Retrieval and Alignment from a Single Imagecited by 66
  19. 2021CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assemblycited by 62
  20. 2021CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsingcited by 51
  21. 2023DiffCAD: Weakly-Supervised Probabilistic CAD Model Retrieval and Alignment from an RGB Imagecited by 48
  22. 2020SceneCAD: Predicting Object Alignments and Layouts in RGB-D Scanscited by 44
  23. 2021Joint Learning of 3D Shape Retrieval and Deformationcited by 41
  24. 2019End-to-End CAD Model Retrieval and 9DoF Alignment in 3D Scanscited by 40
  25. 2023D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropoutscited by 39
  26. 2023Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitivescited by 37
  27. 2021Robust and Accurate Superquadric Recovery: a Probabilistic Approachcited by 29
  28. 2019StructEdit: Learning Structural Shape Variationscited by 23
  29. 2025SuperDec: 3D Scene Decomposition with Superquadric Primitivescited by 19
  30. 2023Marching-Primitives: Shape Abstraction from Signed Distance Functioncited by 18
  31. 2020CAD-Deform: Deformable Fitting of CAD Models to 3D Scanscited by 17
  32. 2023DualVector: Unsupervised Vector Font Synthesis with Dual-Part Representationcited by 16
  33. 2022Primitive-based Shape Abstraction via Nonparametric Bayesian Inferencecited by 14
  34. 2023Iterative Superquadric Recomposition of 3D Objects from Multiple Viewscited by 13
  35. 2023RNb-NeuS: Reflectance and Normal-based Multi-View 3D Reconstructioncited by 13
  36. 2025PrimitiveAnything: Human-Crafted 3D Primitive Assembly Generation with Auto-Regressive Transformercited by 12
  37. 2025Gaussian-Plus-SDF SLAM: High-fidelity 3D Reconstruction at 150+ fpscited by 11
  38. 2024DiffCSG: Differentiable CSG via Rasterizationcited by 6

50 most cited of 51 All 51 (JSON)

Built on by

Not cited yet.