mlsanityData to 7 Oct 2026

Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations

arXiv 2204.08839 ↗First posted 19 Apr 2022cs.CVcited by 65

Not on the map. Why?

Abstract (arXiv)

We propose an unsupervised method for 3D geometry-aware representation learning of articulated objects, in which no image-pose pairs or foreground masks are used for training. Though photorealistic images of articulated objects can be rendered with explicit pose control through existing 3D neural representations, these methods require ground truth 3D pose and foreground masks for training, which are expensive to obtain. We obviate this need by learning the representations with GAN training. The generator is trained to produce realistic images of articulated objects from random poses and latent vectors by adversarial training. To avoid a high computational cost for GAN training, we propose an efficient neural representation for articulated objects based on tri-planes and then present a GAN-based framework for its unsupervised training. Experiments demonstrate the efficiency of our method and show that GAN-based training enables the learning of controllable 3D representations without paired supervision.

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). Builds on 60 of its 77 references that are in the map. First posted on arXiv 19 Apr 2022.

Builds on

60 of 77 references.

References · 60

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  6. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  7. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  8. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  9. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  10. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  11. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  12. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
38 more
  1. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  2. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  3. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  4. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  5. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  6. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  7. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  8. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  9. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  10. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  11. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  12. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  13. 2018Which Training Methods for GANs do actually Converge?cited by 672
  14. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  15. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  16. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 510
  17. 2021AI Choreographer: Music Conditioned 3D Dance Generation with AIST++cited by 479
  18. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  19. 2021Animatable Neural Radiance Fields for Modeling Dynamic Human Bodiescited by 361
  20. 2017Learning from Synthetic Humanscited by 358
  21. 2018Everybody Dance Nowcited by 313
  22. 20163D Menagerie: Modeling the 3D shape and pose of animalscited by 310
  23. 2021A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Posecited by 233
  24. 2021SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapescited by 221
  25. 2021Neural Articulated Radiance Fieldcited by 196
  26. 2021BANMo: Building Animatable 3D Neural Models from Many Casual Videoscited by 195
  27. 2020STAR: Sparse Trained Articulated Human Body Regressorcited by 194
  28. 2018Escaping Plato's Cave: 3D Shape From Adversarial Renderingcited by 170
  29. 2020BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Imagescited by 166
  30. 2020DeepCap: Monocular Human Performance Capture Using Weak Supervisioncited by 162
  31. 2021H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motioncited by 157
  32. 2019NASA: Neural Articulated Shape Approximationcited by 149
  33. 2021Real-time Deep Dynamic Characterscited by 133
  34. 2018A Variational U-Net for Conditional Appearance and Shape Generationcited by 124
  35. 2018Visual Object Networks: Image Generation with Disentangled 3D Representationcited by 124
  36. 20163D Shape Induction from 2D Views of Multiple Objectscited by 121
  37. 2018Detailed Human Avatars from Monocular Videocited by 109
  38. 2021Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothingcited by 102

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 14; 2023: 32; 2024: 12; 2025: 6; 2026: 1.

65 papers.

Sort:

By area:

  1. 2022ECON: Explicit Clothed humans Optimized via Normal integrationcited by 199
  2. 2023DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Modelscited by 154
  3. 2022InstantAvatar: Learning Avatars from Monocular Video in 60 Secondscited by 138
  4. 2022Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatarscited by 124
  5. 2022EVA3D: Compositional 3D Human Generation from 2D Image Collectionscited by 111
  6. 2023TeCH: Text-guided Reconstruction of Lifelike Clothed Humanscited by 104
  7. 2022Generative Neural Articulated Radiance Fieldscited by 101
  8. 2023PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360circcited by 93
  9. 2024Advances in 3D Generation: A Surveycited by 62
  10. 2023Gaussian Shell Maps for Efficient 3D Human Generationcited by 61
  11. 2023Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstructioncited by 60
  12. 2022AvatarGen: A 3D Generative Model for Animatable Human Avatarscited by 59
38 more
  1. 2022AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatarscited by 55
  2. 2022Fast-SNARF: A Fast Deformer for Articulated Neural Fieldscited by 55
  3. 2023AG3D: Learning to Generate 3D Avatars from 2D Image Collectionscited by 55
  4. 2023Learning Locally Editable Virtual Humanscited by 54
  5. 2024PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observationscited by 51
  6. 2023Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstructioncited by 42
  7. 2022HumanGen: Generating Human Radiance Fields with Explicit Priorscited by 33
  8. 2023PrimDiffusion: Volumetric Primitives Diffusion for 3D Human Generationcited by 33
  9. 2023Disentangled Clothed Avatar Generation from Text Descriptionscited by 33
  10. 2023Human101: Training 100+FPS Human Gaussians in 100s from 1 Viewcited by 32
  11. 2023TriHuman : A Real-time and Controllable Tri-plane Representation for Detailed Human Geometry and Appearance Synthesiscited by 28
  12. 2024Recent Trends in 3D Reconstruction of General Non-Rigid Scenescited by 28
  13. 2023GETAvatar: Generative Textured Meshes for Animatable Human Avatarscited by 27
  14. 2023UrbanGIRAFFE: Representing Urban Scenes as Compositional Generative Neural Feature Fieldscited by 26
  15. 2023NPC: Neural Point Characters from Videocited by 26
  16. 2023TOSS:High-quality Text-guided Novel View Synthesis from a Single Imagecited by 26
  17. 2023HumanLiff: Layer-wise 3D Human Generation with Diffusion Modelcited by 23
  18. 20223DHumanGAN: 3D-Aware Human Image Generation with 3D Pose Mappingcited by 17
  19. 2023XAGen: 3D Expressive Human Avatars Generationcited by 17
  20. 2024StructLDM: Structured Latent Diffusion for 3D Human Generationcited by 17
  21. 2023TriVol: Point Cloud Rendering via Triple Volumescited by 16
  22. 2023AniPortraitGAN: Animatable 3D Portrait Generation from 2D Image Collectionscited by 16
  23. 2023Template-free Articulated Neural Point Clouds for Reposable View Synthesiscited by 15
  24. 2023LumiGAN: Unconditional Generation of Relightable 3D Human Facescited by 14
  25. 2023Efficient 3D Articulated Human Generation with Layered Surface Volumescited by 13
  26. 2024A Survey on 3D Human Avatar Modeling -- From Reconstruction to Generationcited by 13
  27. 2024E3Gen: Efficient, Expressive and Editable Avatars Generationcited by 10
  28. 2022Placing Human Animations into 3D Scenes by Learning Interaction- and Geometry-Driven Keyframescited by 8
  29. 2023VeRi3D: Generative Vertex-based Radiance Fields for 3D Controllable Human Image Synthesiscited by 8
  30. 2023AttriHuman-3D: Editable 3D Human Avatar Generation with Attribute Decomposition and Indexingcited by 8
  31. 2025MoGA: 3D Generative Avatar Prior for Monocular Gaussian Avatar Reconstructioncited by 8
  32. 2025MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamicscited by 8
  33. 2023SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshescited by 7
  34. 2024ConsistentAvatar: Learning to Diffuse Fully Consistent Talking Head Avatar with Temporal Guidancecited by 7
  35. 2025Disentangled Clothed Avatar Generation with Layered Representationcited by 7
  36. 2023Articulated 3D Head Avatar Generation using Text-to-Image Diffusion Modelscited by 6
  37. 2023OrthoPlanes: A Novel Representation for Better 3D-Awareness of GANscited by 6
  38. 2023Joint2Human: High-quality 3D Human Generation via Compact Spherical Embedding of 3D Jointscited by 6

50 most cited of 65 All 65 (JSON)