mlsanityData to 7 Oct 2026

InsetGAN for Full-Body Image Generation

arXiv 2203.07293 ↗First posted 14 Mar 2022cs.CV cs.GR cs.LGcited by 45

Not on the map. Why?

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.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). Builds on 30 of its 35 references that are in the map. First posted on arXiv 14 Mar 2022.

Builds on

30 of 35 references.

References · 30

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2022Generative Adversarial Networkscited by 5,603
  4. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  5. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  6. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  7. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  8. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  9. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
  10. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  11. 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
  12. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
18 more
  1. 2021Designing an Encoder for StyleGAN Image Manipulationcited by 542
  2. 2021GAN Inversion: A Surveycited by 366
  3. 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358
  4. 2019Image2StyleGAN++: How to Edit the Embedded Images?cited by 356
  5. 2017Pose Guided Person Image Generationcited by 251
  6. 2021ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinementcited by 248
  7. 2021Large Scale Image Completion via Co-Modulated Generative Adversarial Networkscited by 219
  8. 2020Controllable Person Image Synthesis with Attribute-Decomposed GANcited by 150
  9. 2019Boundless: Generative Adversarial Networks for Image Extensioncited by 62
  10. 2021Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGANcited by 45
  11. 2021TryOnGAN: Body-Aware Try-On via Layered Interpolationcited by 31
  12. 2021Human De-occlusion: Invisible Perception and Recovery for Humanscited by 31
  13. 2021Collaging Class-specific GANs for Semantic Image Synthesiscited by 25
  14. 2019Appearance and Pose-Conditioned Human Image Generation using Deformable GANscited by 24
  15. 2019TileGAN: Synthesis of Large-Scale Non-Homogeneous Texturescited by 15
  16. 2021Learning Realistic Human Reposing using Cyclic Self-Supervision with 3D Shape, Pose, and Appearance Consistencycited by 15
  17. 2019Controllable and Progressive Image Extrapolationcited by 13
  18. 2020Reposing Humans by Warping 3D Featurescited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 13; 2023: 21; 2024: 5; 2025: 5; 2026: 1.

45 papers.

Sort:

By area:

  1. 2022StyleGAN-Human: A Data-Centric Odyssey of Human Generationcited by 143
  2. 2023GP-VTON: Towards General Purpose Virtual Try-on via Collaborative Local-Flow Global-Parsing Learningcited by 120
  3. 2022EVA3D: Compositional 3D Human Generation from 2D Image Collectionscited by 111
  4. 2022Generative Neural Articulated Radiance Fieldscited by 101
  5. 2022AvatarGen: A 3D Generative Model for Animatable Human Avatarscited by 59
  6. 2023MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Capturescited by 54
  7. 2023PrimDiffusion: Volumetric Primitives Diffusion for 3D Human Generationcited by 33
  8. 2022Text2Human: Text-Driven Controllable Human Image Generationcited by 31
  9. 2023DINAR: Diffusion Inpainting of Neural Textures for One-Shot Human Avatarscited by 28
  10. 2024CharacterFactory: Sampling Consistent Characters with GANs for Diffusion Modelscited by 24
  11. 2023HumanLiff: Layer-wise 3D Human Generation with Diffusion Modelcited by 23
  12. 2023Chupa: Carving 3D Clothed Humans from Skinned Shape Priors using 2D Diffusion Probabilistic Modelscited by 20
33 more
  1. 2023Get3DHuman: Lifting StyleGAN-Human into a 3D Generative Model using Pixel-aligned Reconstruction Priorscited by 19
  2. 2023Deep Learning Technique for Human Parsing: A Survey and Outlookcited by 18
  3. 20223DHumanGAN: 3D-Aware Human Image Generation with 3D Pose Mappingcited by 17
  4. 2024StructLDM: Structured Latent Diffusion for 3D Human Generationcited by 17
  5. 2023VIVE3D: Viewpoint-Independent Video Editing using 3D-Aware GANscited by 16
  6. 2023AniPortraitGAN: Animatable 3D Portrait Generation from 2D Image Collectionscited by 16
  7. 2022PASTA-GAN++: A Versatile Framework for High-Resolution Unpaired Virtual Try-oncited by 15
  8. 2023Efficient 3D Articulated Human Generation with Layered Surface Volumescited by 13
  9. 2022HS-Diffusion: Semantic-Mixing Diffusion for Head Swappingcited by 12
  10. 2023FashionTex: Controllable Virtual Try-on with Text and Texturecited by 9
  11. 2023UnitedHuman: Harnessing Multi-Source Data for High-Resolution Human Generationcited by 9
  12. 2025MVHumanNet++: A Large-scale Dataset of Multi-view Daily Dressing Human Captures with Richer Annotations for 3D Human Digitizationcited by 9
  13. 2023VeRi3D: Generative Vertex-based Radiance Fields for 3D Controllable Human Image Synthesiscited by 8
  14. 2023What Decreases Editing Capability? Domain-Specific Hybrid Refinement for Improved GAN Inversioncited by 7
  15. 2023Total Selfie: Generating Full-Body Selfiescited by 5
  16. 2022Synthesizing Photorealistic Virtual Humans Through Cross-modal Disentanglementcited by 4
  17. 2022LSAP: Rethinking Inversion Fidelity, Perception and Editability in GAN Latent Spacecited by 4
  18. 2023Synthesizing Environment-Specific People in Photographscited by 4
  19. 2023VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEscited by 3
  20. 2023FIANCEE: Faster Inference of Adversarial Networks via Conditional Early Exitscited by 3
  21. 2023Synthesizing Anyone, Anywhere, in Any Posecited by 2
  22. 2025Controllable and Expressive One-Shot Video Head Swappingcited by 2
  23. 2022A Survey on Leveraging Pre-trained Generative Adversarial Networks for Image Editing and Restorationcited by 1
  24. 2022Clear Memory-Augmented Auto-Encoder for Surface Defect Detectioncited by 1
  25. 2024Sketch2Human: Deep Human Generation with Disentangled Geometry and Appearance Controlcited by 1
  26. 2022AvatarGen: a 3D Generative Model for Animatable Human Avatarscited by 0
  27. 2023One-Shot Stylization for Full-Body Human Imagescited by 0
  28. 2024CIMGEN: Controlled Image Manipulation by Finetuning Pretrained Generative Models on Limited Datacited by 0
  29. 2024FashionEngine: Interactive 3D Human Generation and Editing via Multimodal Controlscited by 0
  30. 2025Fine-Grained Controllable Apparel Showcase Image Generation via Garment-Centric Outpaintingcited by 0
  31. 2025Exploring Disentangled and Controllable Human Image Synthesis: From End-to-End to Stage-by-Stagecited by 0
  32. 2025FashionMAC: Deformation-Free Fashion Image Generation with Fine-Grained Model Appearance Customizationcited by 0
  33. 2026Generating Key Postures of Bharatanatyam Adavus with Pose Estimationcited by 0