# Improving Human Image Synthesis with Residual Fast Fourier Transformation and Wasserstein Distance

arXiv: https://arxiv.org/abs/2205.12022 · HTML: https://mlsanity.com/paper/2205.12022/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 41 references that are in the map.
- First posted on arXiv 24 May 2022.

## Builds on (most cited first, 28 of 28)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [Regularisation of Neural Networks by Enforcing Lipschitz Continuity](https://mlsanity.com/paper/1804.04368/) (2018)
- [SEAN: Image Synthesis with Semantic Region-Adaptive Normalization](https://mlsanity.com/paper/1911.12861/) (2019)
- [Pose Guided Person Image Generation](https://mlsanity.com/paper/1705.09368/) (2017)
- [PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop](https://mlsanity.com/paper/2103.16507/) (2021)
- [Controllable Person Image Synthesis with Attribute-Decomposed GAN](https://mlsanity.com/paper/2003.12267/) (2020)
- [Progressive Pose Attention Transfer for Person Image Generation](https://mlsanity.com/paper/1904.03349/) (2019)
- [Convergence Analysis of Two-layer Neural Networks with ReLU Activation](https://mlsanity.com/paper/1705.09886/) (2017)
- [Instance-level Human Parsing via Part Grouping Network](https://mlsanity.com/paper/1808.00157/) (2018)
- [XingGAN for Person Image Generation](https://mlsanity.com/paper/2007.09278/) (2020)
- [PISE: Person Image Synthesis and Editing with Decoupled GAN](https://mlsanity.com/paper/2103.04023/) (2021)
- [Deep Spatial Transformation for Pose-Guided Person Image Generation and Animation](https://mlsanity.com/paper/2008.12606/) (2020)
- [DRB-GAN: A Dynamic ResBlock Generative Adversarial Network for Artistic Style Transfer](https://mlsanity.com/paper/2108.07379/) (2021)
- [Bipartite Graph Reasoning GANs for Person Image Generation](https://mlsanity.com/paper/2008.04381/) (2020)
- [PoNA: Pose-guided Non-local Attention for Human Pose Transfer](https://mlsanity.com/paper/2012.07049/) (2020)
- [Metaverse for Social Good: A University Campus Prototype](https://mlsanity.com/paper/2108.08985/) (2021)
- [Speech2Video: Cross-Modal Distillation for Speech to Video Generation](https://mlsanity.com/paper/2107.04806/) (2021)
- [Human Pose Transfer by Adaptive Hierarchical Deformation](https://mlsanity.com/paper/2012.06940/) (2020)
- [Spatial Content Alignment For Pose Transfer](https://mlsanity.com/paper/2103.16828/) (2021)

## Built on by (most cited first, 1 of 1)

- [Pose Guided Human Image Synthesis with Partially Decoupled GAN](https://mlsanity.com/paper/2210.03627/) (2022)

## Abstract (arXiv)

With the rapid development of the Metaverse, virtual humans have emerged, and human image synthesis and editing techniques, such as pose transfer, have recently become popular. Most of the existing techniques rely on GANs, which can generate good human images even with large variants and occlusions. But from our best knowledge, the existing state-of-the-art method still has the following problems: the first is that the rendering effect of the synthetic image is not realistic, such as poor rendering of some regions. And the second is that the training of GAN is unstable and slow to converge, such as model collapse. Based on the above two problems, we propose several methods to solve them. To improve the rendering effect, we use the Residual Fast Fourier Transform Block to replace the traditional Residual Block. Then, spectral normalization and Wasserstein distance are used to improve the speed and stability of GAN training. Experiments demonstrate that the methods we offer are effective at solving the problems listed above, and we get state-of-the-art scores in LPIPS and PSNR.