# Neural Pose Transfer by Spatially Adaptive Instance Normalization

arXiv: https://arxiv.org/abs/2003.07254 · HTML: https://mlsanity.com/paper/2003.07254/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Mar 2020.

## Built on by (most cited first, 30 of 38)

- [TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis](https://mlsanity.com/paper/2305.00976/) (2023)
- [A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation](https://mlsanity.com/paper/2104.07645/) (2021)
- [3D Pose Transfer with Correspondence Learning and Mesh Refinement](https://mlsanity.com/paper/2109.15025/) (2021)
- [Skeleton-free Pose Transfer for Stylized 3D Characters](https://mlsanity.com/paper/2208.00790/) (2022)
- [Learning Compositional Representation for 4D Captures with Neural ODE](https://mlsanity.com/paper/2103.08271/) (2021)
- [Unsupervised 3D Pose Transfer with Cross Consistency and Dual Reconstruction](https://mlsanity.com/paper/2211.10278/) (2022)
- [Intrinsic-Extrinsic Preserved GANs for Unsupervised 3D Pose Transfer](https://mlsanity.com/paper/2108.07520/) (2021)
- [HUMOS: Human Motion Model Conditioned on Body Shape](https://mlsanity.com/paper/2409.03944/) (2024)
- [Zero-shot Pose Transfer for Unrigged Stylized 3D Characters](https://mlsanity.com/paper/2306.00200/) (2023)
- [4DHumanOutfit: a multi-subject 4D dataset of human motion sequences in varying outfits exhibiting large displacements](https://mlsanity.com/paper/2306.07399/) (2023)
- [Weakly-supervised 3D Pose Transfer with Keypoints](https://mlsanity.com/paper/2307.13459/) (2023)
- [Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motions](https://mlsanity.com/paper/2504.03639/) (2025)
- [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)
- [FPRF: Feed-Forward Photorealistic Style Transfer of Large-Scale 3D Neural Radiance Fields](https://mlsanity.com/paper/2401.05516/) (2024)
- [Correspondence-free online human motion retargeting](https://mlsanity.com/paper/2302.00556/) (2023)
- [Neural Human Deformation Transfer](https://mlsanity.com/paper/2109.01588/) (2021)
- [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)
- [RFNet-4D++: Joint Object Reconstruction and Flow Estimation from 4D Point Clouds with Cross-Attention Spatio-Temporal Features](https://mlsanity.com/paper/2203.16482/) (2022)
- [Towards High-Quality 3D Motion Transfer with Realistic Apparel Animation](https://mlsanity.com/paper/2407.11266/) (2024)
- [Smart Fashion: A Review of AI Applications in the Fashion & Apparel Industry](https://mlsanity.com/paper/2111.00905/) (2021)
- [Towards Robust 3D Pose Transfer with Adversarial Learning](https://mlsanity.com/paper/2404.02242/) (2024)
- [SAFIN: Arbitrary Style Transfer With Self-Attentive Factorized Instance Normalization](https://mlsanity.com/paper/2105.06129/) (2021)
- [Image-to-Image Translation with Low Resolution Conditioning](https://mlsanity.com/paper/2107.11262/) (2021)
- [A Neural Anthropometer Learning from Body Dimensions Computed on Human 3D Meshes](https://mlsanity.com/paper/2110.04064/) (2021)
- [MAPConNet: Self-supervised 3D Pose Transfer with Mesh and Point Contrastive Learning](https://mlsanity.com/paper/2304.13819/) (2023)
- [Can Action be Imitated? Learn to Reconstruct and Transfer Human Dynamics from Videos](https://mlsanity.com/paper/2107.11756/) (2021)
- [3D Human Shape Style Transfer](https://mlsanity.com/paper/2109.01587/) (2021)
- [Quality assessment of 3D human animation: Subjective and objective evaluation](https://mlsanity.com/paper/2505.23301/) (2025)

## Abstract (arXiv)

Pose transfer has been studied for decades, in which the pose of a source mesh is applied to a target mesh. Particularly in this paper, we are interested in transferring the pose of source human mesh to deform the target human mesh, while the source and target meshes may have different identity information. Traditional studies assume that the paired source and target meshes are existed with the point-wise correspondences of user annotated landmarks/mesh points, which requires heavy labelling efforts. On the other hand, the generalization ability of deep models is limited, when the source and target meshes have different identities. To break this limitation, we proposes the first neural pose transfer model that solves the pose transfer via the latest technique for image style transfer, leveraging the newly proposed component -- spatially adaptive instance normalization. Our model does not require any correspondences between the source and target meshes. Extensive experiments show that the proposed model can effectively transfer deformation from source to target meshes, and has good generalization ability to deal with unseen identities or poses of meshes. Code is available at https://github.com/jiashunwang/Neural-Pose-Transfer .