# Explicit Disentanglement of Appearance and Perspective in Generative Models

arXiv: https://arxiv.org/abs/1906.11881 · HTML: https://mlsanity.com/paper/1906.11881/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2019.

## Built on by (most cited first, 20 of 20)

- [Diagonal Attention and Style-based GAN for Content-Style Disentanglement in Image Generation and Translation](https://mlsanity.com/paper/2103.16146/) (2021)
- [Symmetry-Based Representations for Artificial and Biological General Intelligence](https://mlsanity.com/paper/2203.09250/) (2022)
- [VTAE: Variational Transformer Autoencoder with Manifolds Learning](https://mlsanity.com/paper/2304.00948/) (2023)
- [Raven's Progressive Matrices Completion with Latent Gaussian Process Priors](https://mlsanity.com/paper/2103.12045/) (2021)
- [Stochastic Video Prediction with Structure and Motion](https://mlsanity.com/paper/2203.10528/) (2022)
- [Closed-Form Diffeomorphic Transformations for Time Series Alignment](https://mlsanity.com/paper/2206.08107/) (2022)
- [Gromov-Wasserstein Autoencoders](https://mlsanity.com/paper/2209.07007/) (2022)
- [Trainable Highly-expressive Activation Functions](https://mlsanity.com/paper/2407.07564/) (2024)
- [Learning Disentangled Representations for Controllable Human Motion Prediction](https://mlsanity.com/paper/2207.01388/) (2022)
- [DisPositioNet: Disentangled Pose and Identity in Semantic Image Manipulation](https://mlsanity.com/paper/2211.05499/) (2022)
- [BInGo: Bayesian Intrinsic Groupwise Registration via Explicit Hierarchical Disentanglement](https://mlsanity.com/paper/2206.02377/) (2022)
- [Compositional Law Parsing with Latent Random Functions](https://mlsanity.com/paper/2209.09115/) (2022)
- [Diffeomorphic Temporal Alignment Nets for Time-series Joint Alignment and Averaging](https://mlsanity.com/paper/2502.06591/) (2025)
- [Identifying Metric Structures of Deep Latent Variable Models](https://mlsanity.com/paper/2502.13757/) (2025)
- [Bayesian Unsupervised Disentanglement of Anatomy and Geometry for Deep Groupwise Image Registration](https://mlsanity.com/paper/2401.02141/) (2024)
- [Distance Weighted Trans Network for Image Completion](https://mlsanity.com/paper/2310.07440/) (2023)
- [DualContrast: Unsupervised Disentangling of Content and Transformations with Implicit Parameterization](https://mlsanity.com/paper/2405.16796/) (2024)
- [Disentangled Human Body Representation Based on Unsupervised Semantic-Aware Learning](https://mlsanity.com/paper/2505.19049/) (2025)
- [DiLO: Disentangled Latent Optimization for Learning Shape and Deformation in Grouped Deforming 3D Objects](https://mlsanity.com/paper/2511.06115/) (2025)
- [Unsupervised SE(3) Disentanglement for in situ Macromolecular Morphology Identification from Cryo-Electron Tomography](https://mlsanity.com/paper/2601.01364/) (2026)

## Abstract (arXiv)

Disentangled representation learning finds compact, independent and easy-to-interpret factors of the data. Learning such has been shown to require an inductive bias, which we explicitly encode in a generative model of images. Specifically, we propose a model with two latent spaces: one that represents spatial transformations of the input data, and another that represents the transformed data. We find that the latter naturally captures the intrinsic appearance of the data. To realize the generative model, we propose a Variationally Inferred Transformational Autoencoder (VITAE) that incorporates a spatial transformer into a variational autoencoder. We show how to perform inference in the model efficiently by carefully designing the encoders and restricting the transformation class to be diffeomorphic. Empirically, our model separates the visual style from digit type on MNIST, separates shape and pose in images of human bodies and facial features from facial shape on CelebA.