# InsetGAN for Full-Body Image Generation

arXiv: https://arxiv.org/abs/2203.07293 · HTML: https://mlsanity.com/paper/2203.07293/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 35 references that are in the map.
- First posted on arXiv 14 Mar 2022.

## Builds on (most cited first, 30 of 30)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Improved Precision and Recall Metric for Assessing Generative Models](https://mlsanity.com/paper/1904.06991/) (2019)
- [Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation](https://mlsanity.com/paper/2008.00951/) (2020)
- [Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?](https://mlsanity.com/paper/1904.03189/) (2019)
- [Designing an Encoder for StyleGAN Image Manipulation](https://mlsanity.com/paper/2102.02766/) (2021)
- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models](https://mlsanity.com/paper/2003.03808/) (2020)
- [Image2StyleGAN++: How to Edit the Embedded Images?](https://mlsanity.com/paper/1911.11544/) (2019)
- [Pose Guided Person Image Generation](https://mlsanity.com/paper/1705.09368/) (2017)
- [ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement](https://mlsanity.com/paper/2104.02699/) (2021)
- [Large Scale Image Completion via Co-Modulated Generative Adversarial Networks](https://mlsanity.com/paper/2103.10428/) (2021)
- [Controllable Person Image Synthesis with Attribute-Decomposed GAN](https://mlsanity.com/paper/2003.12267/) (2020)
- [Boundless: Generative Adversarial Networks for Image Extension](https://mlsanity.com/paper/1908.07007/) (2019)
- [Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN](https://mlsanity.com/paper/2109.06166/) (2021)
- [TryOnGAN: Body-Aware Try-On via Layered Interpolation](https://mlsanity.com/paper/2101.02285/) (2021)
- [Human De-occlusion: Invisible Perception and Recovery for Humans](https://mlsanity.com/paper/2103.11597/) (2021)
- [Collaging Class-specific GANs for Semantic Image Synthesis](https://mlsanity.com/paper/2110.04281/) (2021)
- [Appearance and Pose-Conditioned Human Image Generation using Deformable GANs](https://mlsanity.com/paper/1905.00007/) (2019)
- [TileGAN: Synthesis of Large-Scale Non-Homogeneous Textures](https://mlsanity.com/paper/1904.12795/) (2019)
- [Learning Realistic Human Reposing using Cyclic Self-Supervision with 3D Shape, Pose, and Appearance Consistency](https://mlsanity.com/paper/2110.05458/) (2021)
- [Controllable and Progressive Image Extrapolation](https://mlsanity.com/paper/1912.11711/) (2019)
- [Reposing Humans by Warping 3D Features](https://mlsanity.com/paper/2006.04898/) (2020)

## Built on by (most cited first, 30 of 45)

- [StyleGAN-Human: A Data-Centric Odyssey of Human Generation](https://mlsanity.com/paper/2204.11823/) (2022)
- [GP-VTON: Towards General Purpose Virtual Try-on via Collaborative Local-Flow Global-Parsing Learning](https://mlsanity.com/paper/2303.13756/) (2023)
- [EVA3D: Compositional 3D Human Generation from 2D Image Collections](https://mlsanity.com/paper/2210.04888/) (2022)
- [Generative Neural Articulated Radiance Fields](https://mlsanity.com/paper/2206.14314/) (2022)
- [AvatarGen: A 3D Generative Model for Animatable Human Avatars](https://mlsanity.com/paper/2211.14589/) (2022)
- [MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures](https://mlsanity.com/paper/2312.02963/) (2023)
- [PrimDiffusion: Volumetric Primitives Diffusion for 3D Human Generation](https://mlsanity.com/paper/2312.04559/) (2023)
- [Text2Human: Text-Driven Controllable Human Image Generation](https://mlsanity.com/paper/2205.15996/) (2022)
- [DINAR: Diffusion Inpainting of Neural Textures for One-Shot Human Avatars](https://mlsanity.com/paper/2303.09375/) (2023)
- [CharacterFactory: Sampling Consistent Characters with GANs for Diffusion Models](https://mlsanity.com/paper/2404.15677/) (2024)
- [HumanLiff: Layer-wise 3D Human Generation with Diffusion Model](https://mlsanity.com/paper/2308.09712/) (2023)
- [Chupa: Carving 3D Clothed Humans from Skinned Shape Priors using 2D Diffusion Probabilistic Models](https://mlsanity.com/paper/2305.11870/) (2023)
- [Get3DHuman: Lifting StyleGAN-Human into a 3D Generative Model using Pixel-aligned Reconstruction Priors](https://mlsanity.com/paper/2302.01162/) (2023)
- [Deep Learning Technique for Human Parsing: A Survey and Outlook](https://mlsanity.com/paper/2301.00394/) (2023)
- [3DHumanGAN: 3D-Aware Human Image Generation with 3D Pose Mapping](https://mlsanity.com/paper/2212.07378/) (2022)
- [StructLDM: Structured Latent Diffusion for 3D Human Generation](https://mlsanity.com/paper/2404.01241/) (2024)
- [VIVE3D: Viewpoint-Independent Video Editing using 3D-Aware GANs](https://mlsanity.com/paper/2303.15893/) (2023)
- [AniPortraitGAN: Animatable 3D Portrait Generation from 2D Image Collections](https://mlsanity.com/paper/2309.02186/) (2023)
- [PASTA-GAN++: A Versatile Framework for High-Resolution Unpaired Virtual Try-on](https://mlsanity.com/paper/2207.13475/) (2022)
- [HS-Diffusion: Semantic-Mixing Diffusion for Head Swapping](https://mlsanity.com/paper/2212.06458/) (2022)
- [Efficient 3D Articulated Human Generation with Layered Surface Volumes](https://mlsanity.com/paper/2307.05462/) (2023)
- [FashionTex: Controllable Virtual Try-on with Text and Texture](https://mlsanity.com/paper/2305.04451/) (2023)
- [UnitedHuman: Harnessing Multi-Source Data for High-Resolution Human Generation](https://mlsanity.com/paper/2309.14335/) (2023)
- [MVHumanNet++: A Large-scale Dataset of Multi-view Daily Dressing Human Captures with Richer Annotations for 3D Human Digitization](https://mlsanity.com/paper/2505.01838/) (2025)
- [VeRi3D: Generative Vertex-based Radiance Fields for 3D Controllable Human Image Synthesis](https://mlsanity.com/paper/2309.04800/) (2023)
- [What Decreases Editing Capability? Domain-Specific Hybrid Refinement for Improved GAN Inversion](https://mlsanity.com/paper/2301.12141/) (2023)
- [Total Selfie: Generating Full-Body Selfies](https://mlsanity.com/paper/2308.14740/) (2023)
- [Synthesizing Photorealistic Virtual Humans Through Cross-modal Disentanglement](https://mlsanity.com/paper/2209.01320/) (2022)
- [LSAP: Rethinking Inversion Fidelity, Perception and Editability in GAN Latent Space](https://mlsanity.com/paper/2209.12746/) (2022)
- [Synthesizing Environment-Specific People in Photographs](https://mlsanity.com/paper/2312.14579/) (2023)

## Abstract (arXiv)

While GANs can produce photo-realistic images in ideal conditions for certain domains, the generation of full-body human images remains difficult due to the diversity of identities, hairstyles, clothing, and the variance in pose. Instead of modeling this complex domain with a single GAN, we propose a novel method to combine multiple pretrained GANs, where one GAN generates a global canvas (e.g., human body) and a set of specialized GANs, or insets, focus on different parts (e.g., faces, shoes) that can be seamlessly inserted onto the global canvas. We model the problem as jointly exploring the respective latent spaces such that the generated images can be combined, by inserting the parts from the specialized generators onto the global canvas, without introducing seams. We demonstrate the setup by combining a full body GAN with a dedicated high-quality face GAN to produce plausible-looking humans. We evaluate our results with quantitative metrics and user studies.