mlsanityData to 14 Oct 2026

NAISR: A 3D Neural Additive Model for Interpretable Shape Representation

arXiv 2303.09234 ↗First posted 16 Mar 2023cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Deep implicit functions (DIFs) have emerged as a powerful paradigm for many computer vision tasks such as 3D shape reconstruction, generation, registration, completion, editing, and understanding. However, given a set of 3D shapes with associated covariates there is at present no shape representation method which allows to precisely represent the shapes while capturing the individual dependencies on each covariate. Such a method would be of high utility to researchers to discover knowledge hidden in a population of shapes. For scientific shape discovery, we propose a 3D Neural Additive Model for Interpretable Shape Representation (textttNAISR) which describes individual shapes by deforming a shape atlas in accordance to the effect of disentangled covariates. Our approach captures shape population trends and allows for patient-specific predictions through shape transfer. textttNAISR is the first approach to combine the benefits of deep implicit shape representations with an atlas deforming according to specified covariates. We evaluate textttNAISR with respect to shape reconstruction, shape disentanglement, shape evolution, and shape transfer on three datasets: 1) textitStarman, a simulated 2D shape dataset; 2) the ADNI hippocampus 3D shape dataset; and 3) a pediatric airway 3D shape dataset. Our experiments demonstrate that textitStarman achieves excellent shape reconstruction performance while retaining interpretability. Our code is available at hrefhttps://github.com/uncbiag/NAISRhttps://github.com/uncbiag/NAISR.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 60 of its 101 references that are in the map. First posted on arXiv 16 Mar 2023.

Builds on

60 of 101 references.

References · 60

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  3. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  4. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  5. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  6. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  7. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  8. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  9. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
  10. 2020Implicit Geometric Regularization for Learning Shapescited by 710
  11. 2019TabNet: Attentive Interpretable Tabular Learningcited by 648
  12. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
38 more
  1. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  2. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 460
  3. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  4. 2021Animatable Neural Radiance Fields for Modeling Dynamic Human Bodiescited by 361
  5. 2020Neural Additive Models: Interpretable Machine Learning with Neural Netscited by 319
  6. 2021SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapescited by 221
  7. 2021Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulationcited by 209
  8. 2019NASA: Neural Articulated Shape Approximationcited by 149
  9. 2022NeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editingcited by 142
  10. 2018Disentangled Representation Learning for Non-Parallel Text Style Transfercited by 127
  11. 2020Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondencecited by 119
  12. 2021A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representationcited by 114
  13. 2019Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformationcited by 103
  14. 2022DeVRF: Fast Deformable Voxel Radiance Fields for Dynamic Scenescited by 103
  15. 2021GAN-Control: Explicitly Controllable GANscited by 91
  16. 2021NPMs: Neural Parametric Models for 3D Deformable Shapescited by 90
  17. 2020Deep Implicit Templates for 3D Shape Representationcited by 86
  18. 2020Causal Interpretability for Machine Learning -- Problems, Methods and Evaluationcited by 82
  19. 2020PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representationscited by 81
  20. 2018Unsupervised Discovery of Object Landmarks as Structural Representationscited by 73
  21. 2019Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformationcited by 71
  22. 2020Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloudcited by 71
  23. 2019Disentangled Representation Learning in Cardiac Image Analysiscited by 69
  24. 2018Learning Shape Priors for Single-View 3D Completion and Reconstructioncited by 68
  25. 2019Learning Conditional Deformable Templates with Convolutional Networkscited by 65
  26. 2018Learning to Reconstruct Shapes from Unseen Classescited by 60
  27. 2020Guided Variational Autoencoder for Disentanglement Learningcited by 57
  28. 2022CaDeX: Learning Canonical Deformation Coordinate Space for Dynamic Surface Representation via Neural Homeomorphismcited by 57
  29. 2022Self-supervised Neural Articulated Shape and Appearance Modelscited by 51
  30. 2021Towards Better Explanations of Class Activation Mappingcited by 47
  31. 20223D Shape Reconstruction from 2D Images with Disentangled Attribute Flowcited by 45
  32. 2022textttGradICON: Approximate Diffeomorphisms via Gradient Inverse Consistencycited by 41
  33. 2022Disentangled3D: Learning a 3D Generative Model with Disentangled Geometry and Appearance from Monocular Imagescited by 39
  34. 2022Topology-Preserving Shape Reconstruction and Registration via Neural Diffeomorphic Flowcited by 38
  35. 2018The RBO Dataset of Articulated Objects and Interactionscited by 34
  36. 2022Generalised Implicit Neural Representationscited by 31
  37. 2021Explaining Latent Representations with a Corpus of Examplescited by 30
  38. 2022EditableNeRF: Editing Topologically Varying Neural Radiance Fields by Key Pointscited by 30

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 2.

7 papers.

  1. 2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
  2. 2025Geometric implicit neural representations for signed distance functionscited by 4
  3. 2025Additive Models Explained: A Computational Complexity Approachcited by 3
  4. 2026Provably Explaining Neural Additive Modelscited by 1
  5. 2024NeuralOCT: Airway OCT Analysis via Neural Fieldscited by 0
  6. 2025LucidAtlas: Learning Uncertainty-Aware, Covariate-Disentangled, Individualized Atlas Representationscited by 0
  7. 2026PRISM: A 3D Probabilistic Neural Representation for Interpretable Shape Modelingcited by 0