# Unsupervised Part-Based Disentangling of Object Shape and Appearance

arXiv: https://arxiv.org/abs/1903.06946 · HTML: https://mlsanity.com/paper/1903.06946/

## Key facts

- Cited by 67 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Mar 2019.

## Built on by (most cited first, 30 of 67)

- [Motion Representations for Articulated Animation](https://mlsanity.com/paper/2104.11280/) (2021)
- [PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering](https://mlsanity.com/paper/2103.17070/) (2021)
- [Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression](https://mlsanity.com/paper/2104.02300/) (2021)
- [PartImageNet: A Large, High-Quality Dataset of Parts](https://mlsanity.com/paper/2112.00933/) (2021)
- [Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects](https://mlsanity.com/paper/2112.11347/) (2021)
- [Stochastic Image-to-Video Synthesis using cINNs](https://mlsanity.com/paper/2105.04551/) (2021)
- [Learning Disentangled Representations in the Imaging Domain](https://mlsanity.com/paper/2108.12043/) (2021)
- [Understanding Object Dynamics for Interactive Image-to-Video Synthesis](https://mlsanity.com/paper/2106.11303/) (2021)
- [Test-Time Personalization with a Transformer for Human Pose Estimation](https://mlsanity.com/paper/2107.02133/) (2021)
- [Unsupervised Part Segmentation through Disentangling Appearance and Shape](https://mlsanity.com/paper/2105.12405/) (2021)
- [Danish Fungi 2020 -- Not Just Another Image Recognition Dataset](https://mlsanity.com/paper/2103.10107/) (2021)
- [Position, Padding and Predictions: A Deeper Look at Position Information in CNNs](https://mlsanity.com/paper/2101.12322/) (2021)
- [Unsupervised Human Pose Estimation through Transforming Shape Templates](https://mlsanity.com/paper/2105.04154/) (2021)
- [Unsupervised Foreground Extraction via Deep Region Competition](https://mlsanity.com/paper/2110.15497/) (2021)
- [Symmetry-Based Representations for Artificial and Biological General Intelligence](https://mlsanity.com/paper/2203.09250/) (2022)
- [Self-Supervised Keypoint Discovery in Behavioral Videos](https://mlsanity.com/paper/2112.05121/) (2021)
- [View Generalization for Single Image Textured 3D Models](https://mlsanity.com/paper/2106.06533/) (2021)
- [GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation](https://mlsanity.com/paper/2112.01036/) (2021)
- [Unsupervised Image Representation Learning with Deep Latent Particles](https://mlsanity.com/paper/2205.15821/) (2022)
- [Audio-Visual Face Reenactment](https://mlsanity.com/paper/2210.02755/) (2022)
- [Unsupervised Volumetric Animation](https://mlsanity.com/paper/2301.11326/) (2023)
- [AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints](https://mlsanity.com/paper/2205.10636/) (2022)
- [Scaling-up Disentanglement for Image Translation](https://mlsanity.com/paper/2103.14017/) (2021)
- [Fine Detailed Texture Learning for 3D Meshes with Generative Models](https://mlsanity.com/paper/2203.09362/) (2022)
- [Unsupervised Keypoints from Pretrained Diffusion Models](https://mlsanity.com/paper/2312.00065/) (2023)
- [Behavior-Driven Synthesis of Human Dynamics](https://mlsanity.com/paper/2103.04677/) (2021)
- [Flow Guided Transformable Bottleneck Networks for Motion Retargeting](https://mlsanity.com/paper/2106.07771/) (2021)
- [Part-Based Models Improve Adversarial Robustness](https://mlsanity.com/paper/2209.09117/) (2022)
- [BKinD-3D: Self-Supervised 3D Keypoint Discovery from Multi-View Videos](https://mlsanity.com/paper/2212.07401/) (2022)
- [SC3K: Self-supervised and Coherent 3D Keypoints Estimation from Rotated, Noisy, and Decimated Point Cloud Data](https://mlsanity.com/paper/2308.05410/) (2023)

## Abstract (arXiv)

Large intra-class variation is the result of changes in multiple object characteristics. Images, however, only show the superposition of different variable factors such as appearance or shape. Therefore, learning to disentangle and represent these different characteristics poses a great challenge, especially in the unsupervised case. Moreover, large object articulation calls for a flexible part-based model. We present an unsupervised approach for disentangling appearance and shape by learning parts consistently over all instances of a category. Our model for learning an object representation is trained by simultaneously exploiting invariance and equivariance constraints between synthetically transformed images. Since no part annotation or prior information on an object class is required, the approach is applicable to arbitrary classes. We evaluate our approach on a wide range of object categories and diverse tasks including pose prediction, disentangled image synthesis, and video-to-video translation. The approach outperforms the state-of-the-art on unsupervised keypoint prediction and compares favorably even against supervised approaches on the task of shape and appearance transfer.