mlsanityData to 7 Oct 2026

Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance

arXiv 1806.06503 ↗First posted 18 Jun 2018cs.CVcited by 58

Not on the map. Why?

Abstract (arXiv)

In this work we introduce Deforming Autoencoders, a generative model for images that disentangles shape from appearance in an unsupervised manner. As in the deformable template paradigm, shape is represented as a deformation between a canonical coordinate system (`template') and an observed image, while appearance is modeled in `canonical', template, coordinates, thus discarding variability due to deformations. We introduce novel techniques that allow this approach to be deployed in the setting of autoencoders and show that this method can be used for unsupervised group-wise image alignment. We show experiments with expression morphing in humans, hands, and digits, face manipulation, such as shape and appearance interpolation, as well as unsupervised landmark localization. A more powerful form of unsupervised disentangling becomes possible in template coordinates, allowing us to successfully decompose face images into shading and albedo, and further manipulate face images.

Key facts. Cited by 58 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 18; 2023: 8; 2024: 8; 2025: 4; 2026: 3.

58 papers.

Sort:

By area:

  1. 2022RigNeRF: Fully Controllable Neural 3D Portraitscited by 126
  2. 2021Learning by Watching: Physical Imitation of Manipulation Skills from Human Videoscited by 87
  3. 2022Multiface: A Dataset for Neural Face Renderingcited by 87
  4. 2023A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyondcited by 55
  5. 20223D GAN Inversion for Controllable Portrait Image Animationcited by 53
  6. 2021OpenForensics: Large-Scale Challenging Dataset For Multi-Face Forgery Detection And Segmentation In-The-Wildcited by 50
  7. 2023High-Fidelity and Freely Controllable Talking Head Video Generationcited by 42
  8. 2022Unsupervised Learning of Group Invariant and Equivariant Representationscited by 38
  9. 2021FLAME-in-NeRF : Neural control of Radiance Fields for Free View Face Animationcited by 33
  10. 2021Unsupervised Human Pose Estimation through Transforming Shape Templatescited by 26
  11. 2021ICON: Learning Regular Maps Through Inverse Consistencycited by 26
  12. 2021Learning Facial Representations from the Cycle-consistency of Facecited by 20
38 more
  1. 2021FedDis: Disentangled Federated Learning for Unsupervised Brain Pathology Segmentationcited by 19
  2. 2022Unsupervised Image Representation Learning with Deep Latent Particlescited by 19
  3. 2021Learning monocular 3D reconstruction of articulated categories from motioncited by 18
  4. 2022Part-based Face Recognition with Vision Transformerscited by 18
  5. 2021Learning to Aggregate and Personalize 3D Face from In-the-Wild Photo Collectioncited by 16
  6. 2022Pose-disentangled Contrastive Learning for Self-supervised Facial Representationcited by 16
  7. 2024Rig3DGS: Creating Controllable Portraits from Casual Monocular Videoscited by 16
  8. 2021Image-to-Video Generation via 3D Facial Dynamicscited by 13
  9. 2023Relightable Neural Actor with Intrinsic Decomposition and Pose Controlcited by 11
  10. 2024A Generative Model of Symmetry Transformationscited by 10
  11. 2021Learning Canonical 3D Object Representation for Fine-Grained Recognitioncited by 7
  12. 2021DisUnknown: Distilling Unknown Factors for Disentanglement Learningcited by 6
  13. 2022What do we learn? Debunking the Myth of Unsupervised Outlier Detectioncited by 6
  14. 2024SCE-MAE: Selective Correspondence Enhancement with Masked Autoencoder for Self-Supervised Landmark Estimationcited by 6
  15. 2024NODER: Image Sequence Regression Based on Neural Ordinary Differential Equationscited by 6
  16. 2021LatentKeypointGAN: Controlling Images via Latent Keypointscited by 5
  17. 2024Contrastive Learning of Person-independent Representations for Facial Action Unit Detectioncited by 5
  18. 2021MICS : Multi-steps, Inverse Consistency and Symmetric deep learning registration networkcited by 4
  19. 2022From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark Discoverycited by 4
  20. 2022Contrastive Learning for Diverse Disentangled Foreground Generationcited by 4
  21. 2022DisPositioNet: Disentangled Pose and Identity in Semantic Image Manipulationcited by 4
  22. 2023Rotation and Translation Invariant Representation Learning with Implicit Neural Representationscited by 4
  23. 2023Self-Supervised Detection of Perfect and Partial Input-Dependent Symmetriescited by 4
  24. 2024Explicitly Disentangled Representations in Object-Centric Learningcited by 4
  25. 2021Generating Furry Cars: Disentangling Object Shape & Appearance across Multiple Domainscited by 3
  26. 2022BInGo: Bayesian Intrinsic Groupwise Registration via Explicit Hierarchical Disentanglementcited by 3
  27. 2022Holographic-(V)AE: an end-to-end SO(3)-Equivariant (Variational) Autoencoder in Fourier Spacecited by 3
  28. 2026UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priorscited by 3
  29. 2021Pretrained equivariant features improve unsupervised landmark discoverycited by 2
  30. 2022Robust Deepfake On Unrestricted Media: Generation And Detectioncited by 2
  31. 2022LEAD: Self-Supervised Landmark Estimation by Aligning Distributions of Feature Similaritycited by 2
  32. 2023MetaRegNet: Metamorphic Image Registration Using Flow-Driven Residual Networkscited by 2
  33. 2023Unsupervised Landmark Discovery Using Consistency Guided Bottleneckcited by 1
  34. 2024Bayesian Unsupervised Disentanglement of Anatomy and Geometry for Deep Groupwise Image Registrationcited by 1
  35. 2025DreamTexture: Shape from Virtual Texture with Analysis by Augmentationcited by 1
  36. 2025RECON: Robust symmetry discovery via Explicit Canonical Orientation Normalizationcited by 1
  37. 2026Relit-LiVE: Relight Video by Jointly Learning Environment Videocited by 1
  38. 2021Exploring Deep Registration Latent Spacescited by 0

50 most cited of 58 All 58 (JSON)