# Deformable Generator Networks: Unsupervised Disentanglement of Appearance and Geometry

arXiv: https://arxiv.org/abs/1806.06298 · HTML: https://mlsanity.com/paper/1806.06298/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jun 2018.

## Built on by (most cited first, 10 of 10)

- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [GAN-Supervised Dense Visual Alignment](https://mlsanity.com/paper/2112.05143/) (2021)
- [A Tale of Two Latent Flows: Learning Latent Space Normalizing Flow with Short-run Langevin Flow for Approximate Inference](https://mlsanity.com/paper/2301.09300/) (2023)
- [DEVIAS: Learning Disentangled Video Representations of Action and Scene](https://mlsanity.com/paper/2312.00826/) (2023)
- [LatentKeypointGAN: Controlling Images via Latent Keypoints](https://mlsanity.com/paper/2103.15812/) (2021)
- [Contrastive Learning for Diverse Disentangled Foreground Generation](https://mlsanity.com/paper/2211.02707/) (2022)
- [BInGo: Bayesian Intrinsic Groupwise Registration via Explicit Hierarchical Disentanglement](https://mlsanity.com/paper/2206.02377/) (2022)
- [Langevin Autoencoders for Learning Deep Latent Variable Models](https://mlsanity.com/paper/2209.07036/) (2022)
- [Bayesian Unsupervised Disentanglement of Anatomy and Geometry for Deep Groupwise Image Registration](https://mlsanity.com/paper/2401.02141/) (2024)
- [LatentKeypointGAN: Controlling Images via Latent Keypoints -- Extended Abstract](https://mlsanity.com/paper/2205.03448/) (2022)

## Abstract (arXiv)

We present a deformable generator model to disentangle the appearance and geometric information for both image and video data in a purely unsupervised manner. The appearance generator network models the information related to appearance, including color, illumination, identity or category, while the geometric generator performs geometric warping, such as rotation and stretching, through generating deformation field which is used to warp the generated appearance to obtain the final image or video sequences. Two generators take independent latent vectors as input to disentangle the appearance and geometric information from image or video sequences. For video data, a nonlinear transition model is introduced to both the appearance and geometric generators to capture the dynamics over time. The proposed scheme is general and can be easily integrated into different generative models. An extensive set of qualitative and quantitative experiments shows that the appearance and geometric information can be well disentangled, and the learned geometric generator can be conveniently transferred to other image datasets to facilitate knowledge transfer tasks.