mlsanityData to 7 Oct 2026

3DIAS: 3D Shape Reconstruction with Implicit Algebraic Surfaces

arXiv 2108.08653 ↗First posted 19 Aug 2021cs.CVcited by 17

Not on the map. Why?

Abstract (arXiv)

3D Shape representation has substantial effects on 3D shape reconstruction. Primitive-based representations approximate a 3D shape mainly by a set of simple implicit primitives, but the low geometrical complexity of the primitives limits the shape resolution. Moreover, setting a sufficient number of primitives for an arbitrary shape is challenging. To overcome these issues, we propose a constrained implicit algebraic surface as the primitive with few learnable coefficients and higher geometrical complexities and a deep neural network to produce these primitives. Our experiments demonstrate the superiorities of our method in terms of representation power compared to the state-of-the-art methods in single RGB image 3D shape reconstruction. Furthermore, we show that our method can semantically learn segments of 3D shapes in an unsupervised manner. The code is publicly available from https://myavartanoo.github.io/3dias/ .

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 29 of its 40 references that are in the map. First posted on arXiv 19 Aug 2021.

Builds on

29 of 40 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  5. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  6. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  7. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  8. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  9. 2017End-to-end Recovery of Human Shape and Posecited by 883
  10. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  11. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  12. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
17 more
  1. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  2. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  3. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  4. 2019What Do Single-view 3D Reconstruction Networks Learn?cited by 259
  5. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  6. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  7. 2017Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputscited by 189
  8. 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
  9. 2016Learning a Predictable and Generative Vector Representation for Objectscited by 173
  10. 2019CvxNet: Learnable Convex Decompositioncited by 173
  11. 2016Generative and Discriminative Voxel Modeling with Convolutional Neural Networkscited by 128
  12. 2019Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboidscited by 123
  13. 2017Hierarchical Surface Prediction for 3D Object Reconstructioncited by 89
  14. 2019BAE-NET: Branched Autoencoder for Shape Co-Segmentationcited by 89
  15. 2019Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Eracited by 87
  16. 2018Learning 3D Shape Completion under Weak Supervisioncited by 40
  17. 2017Learning Representations and Generative Models for 3D Point Cloudscited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 6; 2024: 3; 2025: 2; 2026: 2.

17 papers.

Sort:

  1. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 228
  2. 2024SceneDreamer360: Text-Driven 3D-Consistent Scene Generation with Panoramic Gaussian Splattingcited by 24
  3. 2022Few 'Zero Level Set'-Shot Learning of Shape Signed Distance Functions in Feature Spacecited by 22
  4. 2022Latent Partition Implicit with Surface Codes for 3D Representationcited by 21
  5. 2024Unsupervised Occupancy Learning from Sparse Point Cloudcited by 15
  6. 2023Iterative Superquadric Recomposition of 3D Objects from Multiple Viewscited by 13
  7. 2023Mixing-Denoising Generalizable Occupancy Networkscited by 12
  8. 2023Robustifying Generalizable Implicit Shape Networks with a Tunable Non-Parametric Modelcited by 10
  9. 2023Primitive-based 3D Human-Object Interaction Modelling and Programmingcited by 7
  10. 2025Residual Primitive Fitting of 3D Shapes with SuperFrustacited by 5
  11. 2022Primitive3D: 3D Object Dataset Synthesis from Randomly Assembled Primitivescited by 4
  12. 2023CNC-Net: Self-Supervised Learning for CNC Machining Operationscited by 3
5 more
  1. 2022Taylor3DNet: Fast 3D Shape Inference With Landmark Points Based Taylor Seriescited by 0
  2. 2024LISR: Learning Linear 3D Implicit Surface Representation Using Compactly Supported Radial Basis Functionscited by 0
  3. 2025ESCT3D: Efficient and Selectively Controllable Text-Driven 3D Content Generation with Gaussian Splattingcited by 0
  4. 2026Electrostatics-Inspired Surface Reconstruction (EISR): Recovering 3D Shapes as a Superposition of Poisson's PDE Solutionscited by 0
  5. 2026Exact Quotients of Fresnel-Kummer Surfaces and Certified Biaxial Refractioncited by 0