mlsanityData to 7 Oct 2026

A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation

arXiv 2104.07645 ↗First posted 15 Apr 2021cs.CVcited by 113

Not on the map. Why?

Abstract (arXiv)

Recent work has made significant progress on using implicit functions, as a continuous representation for 3D rigid object shape reconstruction. However, much less effort has been devoted to modeling general articulated objects. Compared to rigid objects, articulated objects have higher degrees of freedom, which makes it hard to generalize to unseen shapes. To deal with the large shape variance, we introduce Articulated Signed Distance Functions (A-SDF) to represent articulated shapes with a disentangled latent space, where we have separate codes for encoding shape and articulation. We assume no prior knowledge on part geometry, articulation status, joint type, joint axis, and joint location. With this disentangled continuous representation, we demonstrate that we can control the articulation input and animate unseen instances with unseen joint angles. Furthermore, we propose a Test-Time Adaptation inference algorithm to adjust our model during inference. We demonstrate our model generalize well to out-of-distribution and unseen data, e.g., partial point clouds and real-world depth images.

Key facts. Cited by 113 papers in the map (data through 7 Oct 2026). Builds on 72 of its 96 references that are in the map. First posted on arXiv 15 Apr 2021.

Builds on

72 of 96 references.

References · 72

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017Mask R-CNNcited by 7,259
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  5. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  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. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  11. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
  12. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
38 more
  1. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  2. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  3. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  4. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 691
  5. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  6. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  7. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  8. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
  9. 2018Disentangling by Factorisingcited by 614
  10. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 584
  11. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  12. 2020Local Implicit Grid Representations for 3D Scenescited by 372
  13. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  14. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 332
  15. 2018Everybody Dance Nowcited by 313
  16. 20163D Menagerie: Modeling the 3D shape and pose of animalscited by 310
  17. 2017"Zero-Shot" Super-Resolution using Deep Internal Learningcited by 285
  18. 2018Generating 3D faces using Convolutional Mesh Autoencoderscited by 267
  19. 2019Multi-Garment Net: Learning to Dress 3D People from Imagescited by 244
  20. 2021SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapescited by 221
  21. 2020Swapping Autoencoder for Deep Image Manipulationcited by 215
  22. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  23. 2021Neural Articulated Radiance Fieldcited by 196
  24. 2018Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimationcited by 185
  25. 2019DeepHuman: 3D Human Reconstruction from a Single Imagecited by 182
  26. 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
  27. 2021Where2Act: From Pixels to Actions for Articulated 3D Objectscited by 179
  28. 2020Semantic Photo Manipulation with a Generative Image Priorcited by 178
  29. 2019Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervisioncited by 176
  30. 20193D Hand Shape and Pose Estimation from a Single RGB Imagecited by 174
  31. 2019CvxNet: Learnable Convex Decompositioncited by 173
  32. 2021Hand-Object Contact Consistency Reasoning for Human Grasps Generationcited by 160
  33. 2019Category-Level Articulated Object Pose Estimationcited by 158
  34. 2020Adversarial Latent Autoencoderscited by 155
  35. 2020Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wildcited by 152
  36. 2019NASA: Neural Articulated Shape Approximationcited by 149
  37. 2018BodyNet: Volumetric Inference of 3D Human Body Shapescited by 141
  38. 2018Visual Object Networks: Image Generation with Disentangled 3D Representationcited by 124

50 most cited of 72 All 72 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 22; 2023: 19; 2024: 18; 2025: 27; 2026: 16.

113 papers.

Sort:

By area:

  1. 2021Neural Fields in Visual Computing and Beyondcited by 539
  2. 2022Ditto: Building Digital Twins of Articulated Objects from Interactioncited by 152
  3. 2021Beyond Periodicity: Towards a Unifying Framework for Activations in Coordinate-MLPscited by 134
  4. 2023PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objectscited by 115
  5. 2022Disentangled Representation Learningcited by 111
  6. 2022AKB-48: A Real-World Articulated Object Knowledge Basecited by 81
  7. 2021VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objectscited by 78
  8. 2022Full-Body Articulated Human-Object Interactioncited by 76
  9. 2023Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clipscited by 73
  10. 2025ArtGS: Building Interactable Replicas of Complex Articulated Objects via Gaussian Splattingcited by 67
  11. 2024SINGAPO: Single Image Controlled Generation of Articulated Parts in Objectscited by 66
  12. 2021CoNeRF: Controllable Neural Radiance Fieldscited by 65
38 more
  1. 2023CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objectscited by 64
  2. 2023DexArt: Benchmarking Generalizable Dexterous Manipulation with Articulated Objectscited by 64
  3. 2022LISA: Learning Implicit Shape and Appearance of Handscited by 63
  4. 2022CaDeX: Learning Canonical Deformation Coordinate Space for Dynamic Surface Representation via Neural Homeomorphismcited by 56
  5. 2022CLA-NeRF: Category-Level Articulated Neural Radiance Fieldcited by 55
  6. 2022Self-supervised Neural Articulated Shape and Appearance Modelscited by 51
  7. 2024REACTO: Reconstructing Articulated Objects from a Single Videocited by 45
  8. 2022A Level Set Theory for Neural Implicit Evolution under Explicit Flowscited by 42
  9. 2024HOIDiffusion: Generating Realistic 3D Hand-Object Interaction Datacited by 37
  10. 2022Understanding 3D Object Articulation in Internet Videoscited by 36
  11. 2025ArticulatedGS: Self-supervised Digital Twin Modeling of Articulated Objects using 3D Gaussian Splattingcited by 35
  12. 2023Building Rearticulable Models for Arbitrary 3D Objects from 4D Point Cloudscited by 34
  13. 2021Test-Time Personalization with a Transformer for Human Pose Estimationcited by 33
  14. 2023Understanding 3D Object Interaction from a Single Imagecited by 33
  15. 2023Where2Explore: Few-shot Affordance Learning for Unseen Novel Categories of Articulated Objectscited by 33
  16. 2024Recent Trends in 3D Reconstruction of General Non-Rigid Scenescited by 28
  17. 2023Recurrence without Recurrence: Stable Video Landmark Detection with Deep Equilibrium Modelscited by 26
  18. 2023NAP: Neural 3D Articulation Priorcited by 25
  19. 2026Articraft: An Agentic System for Scalable Articulated 3D Asset Generationcited by 25
  20. 2024Articulate your NeRF: Unsupervised articulated object modeling via conditional view synthesiscited by 24
  21. 2024PhysPart: Physically Plausible Part Completion for Interactable Objectscited by 24
  22. 2025FreeArt3D: Training-Free Articulated Object Generation using 3D Diffusioncited by 22
  23. 2024ArtFormer: Controllable Generation of Diverse 3D Articulated Objectscited by 21
  24. 20233D Implicit Transporter for Temporally Consistent Keypoint Discoverycited by 20
  25. 2025Particulate: Feed-Forward 3D Object Articulationcited by 20
  26. 2023Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariancecited by 19
  27. 2025iTACO: Interactable Digital Twins of Articulated Objects from Casually Captured RGBD Videoscited by 18
  28. 2025GaussianArt: Unified Modeling of Geometry and Motion for Articulated Objectscited by 17
  29. 2022Regularized Deep Signed Distance Fields for Reactive Motion Generationcited by 16
  30. 2023ContactArt: Learning 3D Interaction Priors for Category-level Articulated Object and Hand Poses Estimationcited by 16
  31. 2022Learning Category-Level Generalizable Object Manipulation Policy via Generative Adversarial Self-Imitation Learning from Demonstrationscited by 15
  32. 2025VideoArtGS: Building Digital Twins of Articulated Objects from Monocular Videocited by 15
  33. 2024Survey on Modeling of Human-made Articulated Objectscited by 14
  34. 2022Unsupervised Kinematic Motion Detection for Part-segmented 3D Shape Collectionscited by 13
  35. 2025Detection Based Part-level Articulated Object Reconstruction from Single RGBD Imagecited by 13
  36. 2025SplArt: Articulation Estimation and Part-Level Reconstruction with 3D Gaussian Splattingcited by 13
  37. 2021OMAD: Object Model with Articulated Deformations for Pose Estimation and Retrievalcited by 12
  38. 2022An Implicit Parametric Morphable Dental Modelcited by 12

50 most cited of 113 All 113 (JSON)