# Liquid Warping GAN with Attention: A Unified Framework for Human Image Synthesis

arXiv: https://arxiv.org/abs/2011.09055 · HTML: https://mlsanity.com/paper/2011.09055/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2020.

## Built on by (most cited first, 26 of 26)

- [Animatable Neural Radiance Fields from Monocular RGB Videos](https://mlsanity.com/paper/2106.13629/) (2021)
- [SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction](https://mlsanity.com/paper/2312.06704/) (2023)
- [Single-Image 3D Human Digitization with Shape-Guided Diffusion](https://mlsanity.com/paper/2311.09221/) (2023)
- [TryOnGAN: Body-Aware Try-On via Layered Interpolation](https://mlsanity.com/paper/2101.02285/) (2021)
- [3D-Aware Semantic-Guided Generative Model for Human Synthesis](https://mlsanity.com/paper/2112.01422/) (2021)
- [Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer](https://mlsanity.com/paper/2307.07754/) (2023)
- [Template-Free Single-View 3D Human Digitalization with Diffusion-Guided LRM](https://mlsanity.com/paper/2401.12175/) (2024)
- [Copy Motion From One to Another: Fake Motion Video Generation](https://mlsanity.com/paper/2205.01373/) (2022)
- [Dancing Avatar: Pose and Text-Guided Human Motion Videos Synthesis with Image Diffusion Model](https://mlsanity.com/paper/2308.07749/) (2023)
- [UniHuman: A Unified Model for Editing Human Images in the Wild](https://mlsanity.com/paper/2312.14985/) (2023)
- [Human Image Generation: A Comprehensive Survey](https://mlsanity.com/paper/2212.08896/) (2022)
- [CharacterGAN: Few-Shot Keypoint Character Animation and Reposing](https://mlsanity.com/paper/2102.03141/) (2021)
- [Collaborative Neural Rendering using Anime Character Sheets](https://mlsanity.com/paper/2207.05378/) (2022)
- [Do As I Do: Pose Guided Human Motion Copy](https://mlsanity.com/paper/2406.16601/) (2024)
- [Collecting The Puzzle Pieces: Disentangled Self-Driven Human Pose Transfer by Permuting Textures](https://mlsanity.com/paper/2210.01887/) (2022)
- [DiffBody: Diffusion-based Pose and Shape Editing of Human Images](https://mlsanity.com/paper/2401.02804/) (2024)
- [Delving into the Frequency: Temporally Consistent Human Motion Transfer in the Fourier Space](https://mlsanity.com/paper/2209.00233/) (2022)
- [Controllable Person Image Synthesis with Spatially-Adaptive Warped Normalization](https://mlsanity.com/paper/2105.14739/) (2021)
- [Enhanced Multi-Scale Cross-Attention for Person Image Generation](https://mlsanity.com/paper/2501.08900/) (2025)
- [DRaCoN -- Differentiable Rasterization Conditioned Neural Radiance Fields for Articulated Avatars](https://mlsanity.com/paper/2203.15798/) (2022)
- [Masked Discriminators for Content-Consistent Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2309.13188/) (2023)
- [Adaptive Multi-Modal Control of Digital Human Hand Synthesis Using a Region-Aware Cycle Loss](https://mlsanity.com/paper/2409.09149/) (2024)
- [One-Shot Novel View and Pose Human Image Synthesis via 3D Prior Guided Diffusion Model](https://mlsanity.com/paper/2606.19718/) (2026)
- [A Survey of Body and Face Motion: Datasets, Performance Evaluation Metrics and Generative Techniques](https://mlsanity.com/paper/2512.09005/) (2025)
- [DISPLAY: Directable Human-Object Interaction Video Generation via Sparse Motion Guidance and Multi-Task Auxiliary](https://mlsanity.com/paper/2603.09883/) (2026)
- [EMOSH: Expressive Motion and Shape Disentanglement for Human Animation](https://mlsanity.com/paper/2606.28026/) (2026)

## Abstract (arXiv)

We tackle human image synthesis, including human motion imitation, appearance transfer, and novel view synthesis, within a unified framework. It means that the model, once being trained, can be used to handle all these tasks. The existing task-specific methods mainly use 2D keypoints to estimate the human body structure. However, they only express the position information with no abilities to characterize the personalized shape of the person and model the limb rotations. In this paper, we propose to use a 3D body mesh recovery module to disentangle the pose and shape. It can not only model the joint location and rotation but also characterize the personalized body shape. To preserve the source information, such as texture, style, color, and face identity, we propose an Attentional Liquid Warping GAN with Attentional Liquid Warping Block (AttLWB) that propagates the source information in both image and feature spaces to the synthesized reference. Specifically, the source features are extracted by a denoising convolutional auto-encoder for characterizing the source identity well. Furthermore, our proposed method can support a more flexible warping from multiple sources. To further improve the generalization ability of the unseen source images, a one/few-shot adversarial learning is applied. In detail, it firstly trains a model in an extensive training set. Then, it finetunes the model by one/few-shot unseen image(s) in a self-supervised way to generate high-resolution (512 x 512 and 1024 x 1024) results. Also, we build a new dataset, namely iPER dataset, for the evaluation of human motion imitation, appearance transfer, and novel view synthesis. Extensive experiments demonstrate the effectiveness of our methods in terms of preserving face identity, shape consistency, and clothes details. All codes and dataset are available on https://impersonator.org/work/impersonator-plus-plus.html.