# Intrinsic-Extrinsic Preserved GANs for Unsupervised 3D Pose Transfer

arXiv: https://arxiv.org/abs/2108.07520 · HTML: https://mlsanity.com/paper/2108.07520/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 42 references that are in the map.
- First posted on arXiv 17 Aug 2021.

## Builds on (most cited first, 24 of 24)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [Semantic Scene Completion from a Single Depth Image](https://mlsanity.com/paper/1611.08974/) (2016)
- [Swapping Autoencoder for Deep Image Manipulation](https://mlsanity.com/paper/2007.00653/) (2020)
- [Deep Parametric Continuous Convolutional Neural Networks](https://mlsanity.com/paper/2101.06742/) (2021)
- [3D-CODED : 3D Correspondences by Deep Deformation](https://mlsanity.com/paper/1806.05228/) (2018)
- [Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network](https://mlsanity.com/paper/1811.02565/) (2018)
- [XingGAN for Person Image Generation](https://mlsanity.com/paper/2007.09278/) (2020)
- [Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation](https://mlsanity.com/paper/1804.01110/) (2018)
- [Unsupervised Shape and Pose Disentanglement for 3D Meshes](https://mlsanity.com/paper/2007.11341/) (2020)
- [LIMP: Learning Latent Shape Representations with Metric Preservation Priors](https://mlsanity.com/paper/2003.12283/) (2020)
- [TextureGAN: Controlling Deep Image Synthesis with Texture Patches](https://mlsanity.com/paper/1706.02823/) (2017)
- [Neural Pose Transfer by Spatially Adaptive Instance Normalization](https://mlsanity.com/paper/2003.07254/) (2020)
- [Cycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image Generation](https://mlsanity.com/paper/1908.00999/) (2019)
- [Bipartite Graph Reasoning GANs for Person Image Generation](https://mlsanity.com/paper/2008.04381/) (2020)
- [Geometric Disentanglement for Generative Latent Shape Models](https://mlsanity.com/paper/1908.06386/) (2019)
- [MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation](https://mlsanity.com/paper/1911.11758/) (2019)
- [Controllable Person Image Synthesis with Spatially-Adaptive Warped Normalization](https://mlsanity.com/paper/2105.14739/) (2021)

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

- [Underwater Light Field Retention : Neural Rendering for Underwater Imaging](https://mlsanity.com/paper/2203.11006/) (2022)
- [Unsupervised 3D Pose Transfer with Cross Consistency and Dual Reconstruction](https://mlsanity.com/paper/2211.10278/) (2022)
- [Zero-shot Pose Transfer for Unrigged Stylized 3D Characters](https://mlsanity.com/paper/2306.00200/) (2023)
- [Weakly-supervised 3D Pose Transfer with Keypoints](https://mlsanity.com/paper/2307.13459/) (2023)
- [AniFormer: Data-driven 3D Animation with Transformer](https://mlsanity.com/paper/2110.10533/) (2021)
- [Geometry-Contrastive Transformer for Generalized 3D Pose Transfer](https://mlsanity.com/paper/2112.07374/) (2021)
- [Layout-to-Image Translation with Double Pooling Generative Adversarial Networks](https://mlsanity.com/paper/2108.12900/) (2021)
- [Correspondence-free online human motion retargeting](https://mlsanity.com/paper/2302.00556/) (2023)
- [ShapeFusion: A 3D diffusion model for localized shape editing](https://mlsanity.com/paper/2403.19773/) (2024)
- [3D Generative Model Latent Disentanglement via Local Eigenprojection](https://mlsanity.com/paper/2302.12798/) (2023)
- [HMC: Hierarchical Mesh Coarsening for Skeleton-free Motion Retargeting](https://mlsanity.com/paper/2303.10941/) (2023)
- [Neural Pose Representation Learning for Generating and Transferring Non-Rigid Object Poses](https://mlsanity.com/paper/2406.09728/) (2024)
- [Towards Robust 3D Pose Transfer with Adversarial Learning](https://mlsanity.com/paper/2404.02242/) (2024)
- [DiffSurf: A Transformer-based Diffusion Model for Generating and Reconstructing 3D Surfaces in Pose](https://mlsanity.com/paper/2408.14860/) (2024)
- [MeshMamba: State Space Models for Articulated 3D Mesh Generation and Reconstruction](https://mlsanity.com/paper/2507.15212/) (2025)
- [From Local Binary Patterns to Pixel Difference Networks for Efficient Visual Representation Learning](https://mlsanity.com/paper/2303.08414/) (2023)
- [MimiCAT: Mimic with Correspondence-Aware Cascade-Transformer for Category-Free 3D Pose Transfer](https://mlsanity.com/paper/2511.18370/) (2025)
- [DSFFNet: Dual-Side Feature Fusion Network for 3D Pose Transfer](https://mlsanity.com/paper/2305.14951/) (2023)
- [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)

## Abstract (arXiv)

With the strength of deep generative models, 3D pose transfer regains intensive research interests in recent years. Existing methods mainly rely on a variety of constraints to achieve the pose transfer over 3D meshes, e.g., the need for manually encoding for shape and pose disentanglement. In this paper, we present an unsupervised approach to conduct the pose transfer between any arbitrate given 3D meshes. Specifically, a novel Intrinsic-Extrinsic Preserved Generative Adversarial Network (IEP-GAN) is presented for both intrinsic (i.e., shape) and extrinsic (i.e., pose) information preservation. Extrinsically, we propose a co-occurrence discriminator to capture the structural/pose invariance from distinct Laplacians of the mesh. Meanwhile, intrinsically, a local intrinsic-preserved loss is introduced to preserve the geodesic priors while avoiding heavy computations. At last, we show the possibility of using IEP-GAN to manipulate 3D human meshes in various ways, including pose transfer, identity swapping and pose interpolation with latent code vector arithmetic. The extensive experiments on various 3D datasets of humans, animals and hands qualitatively and quantitatively demonstrate the generality of our approach. Our proposed model produces better results and is substantially more efficient compared to recent state-of-the-art methods. Code is available: https://github.com/mikecheninoulu/Unsupervised_IEPGAN