mlsanityData to 7 Oct 2026

Cross Attention Based Style Distribution for Controllable Person Image Synthesis

arXiv 2208.00712 ↗First posted 1 Aug 2022cs.CVcited by 45

Not on the map. Why?

Abstract (arXiv)

Controllable person image synthesis task enables a wide range of applications through explicit control over body pose and appearance. In this paper, we propose a cross attention based style distribution module that computes between the source semantic styles and target pose for pose transfer. The module intentionally selects the style represented by each semantic and distributes them according to the target pose. The attention matrix in cross attention expresses the dynamic similarities between the target pose and the source styles for all semantics. Therefore, it can be utilized to route the color and texture from the source image, and is further constrained by the target parsing map to achieve a clearer objective. At the same time, to encode the source appearance accurately, the self attention among different semantic styles is also added. The effectiveness of our model is validated quantitatively and qualitatively on pose transfer and virtual try-on tasks.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). Builds on 45 of its 51 references that are in the map. First posted on arXiv 1 Aug 2022.

Builds on

45 of 51 references.

References · 45

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  7. 2020End-to-End Object Detection with Transformerscited by 7,384
  8. 2017Squeeze-and-Excitation Networkscited by 4,763
  9. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  10. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  11. 2017Non-local Neural Networkscited by 2,290
  12. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
33 more
  1. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  2. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  3. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  4. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 717
  5. 2017Person Transfer GAN to Bridge Domain Gap for Person Re-Identificationcited by 479
  6. 2017VITON: An Image-based Virtual Try-on Networkcited by 285
  7. 2017Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitrocited by 280
  8. 2017Pose Guided Person Image Generationcited by 251
  9. 2018Toward Characteristic-Preserving Image-based Virtual Try-On Networkcited by 192
  10. 2017Deformable GANs for Pose-based Human Image Generationcited by 166
  11. 2019Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesiscited by 161
  12. 2020Controllable Person Image Synthesis with Attribute-Decomposed GANcited by 150
  13. 2021Parser-Free Virtual Try-on via Distilling Appearance Flowscited by 142
  14. 2019Progressive Pose Attention Transfer for Person Image Generationcited by 138
  15. 2018The Contextual Loss for Image Transformation with Non-Aligned Datacited by 135
  16. 2018A Variational U-Net for Conditional Appearance and Shape Generationcited by 124
  17. 2020Cross-domain Correspondence Learning for Exemplar-based Image Translationcited by 116
  18. 2017Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsingcited by 109
  19. 2019Dense Intrinsic Appearance Flow for Human Pose Transfercited by 104
  20. 2020Deep Image Spatial Transformation for Person Image Generationcited by 100
  21. 2017Disentangled Person Image Generationcited by 98
  22. 2018Synthesizing Images of Humans in Unseen Posescited by 96
  23. 2020XingGAN for Person Image Generationcited by 81
  24. 2018FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identificationcited by 70
  25. 2018Pose Guided Human Video Generationcited by 67
  26. 2021PISE: Person Image Synthesis and Editing with Decoupled GANcited by 62
  27. 2018Unsupervised Person Image Synthesis in Arbitrary Posescited by 55
  28. 2021Learning Semantic Person Image Generation by Region-Adaptive Normalizationcited by 44
  29. 2021DRB-GAN: A Dynamic ResBlock Generative Adversarial Network for Artistic Style Transfercited by 38
  30. 2019Unsupervised Person Image Generation with Semantic Parsing Transformationcited by 32
  31. 2020Towards Fine-grained Human Pose Transfer with Detail Replenishing Networkcited by 21
  32. 2021Learning Realistic Human Reposing using Cyclic Self-Supervision with 3D Shape, Pose, and Appearance Consistencycited by 15
  33. 2020Novel View Synthesis on Unpaired Data by Conditional Deformable Variational Auto-Encodercited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 12; 2024: 19; 2025: 6; 2026: 2.

45 papers.

Sort:

By area:

  1. 2022Person Image Synthesis via Denoising Diffusion Modelcited by 104
  2. 2023HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generationcited by 104
  3. 2023Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Modelscited by 104
  4. 2024Deepfake Generation and Detection: A Benchmark and Surveycited by 66
  5. 2024Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesiscited by 48
  6. 2024Learning Flow Fields in Attention for Controllable Person Image Generationcited by 27
  7. 2024MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinementcited by 24
  8. 2024GaussianVTON: 3D Human Virtual Try-ON via Multi-Stage Gaussian Splatting Editing with Image Promptingcited by 22
  9. 2024Towards Effective Usage of Human-Centric Priors in Diffusion Models for Text-based Human Image Generationcited by 17
  10. 2024Giving a Hand to Diffusion Models: a Two-Stage Approach to Improving Conditional Human Image Generationcited by 13
  11. 2023UPGPT: Universal Diffusion Model for Person Image Generation, Editing and Pose Transfercited by 12
  12. 2023UniHuman: A Unified Model for Editing Human Images in the Wildcited by 12
33 more
  1. 2024Cross-view Masked Diffusion Transformers for Person Image Synthesiscited by 12
  2. 2022HumanDiffusion: a Coarse-to-Fine Alignment Diffusion Framework for Controllable Text-Driven Person Image Generationcited by 11
  3. 2022Human Image Generation: A Comprehensive Surveycited by 11
  4. 2024DiffLoRA: Generating Personalized Low-Rank Adaptation Weights with Diffusioncited by 11
  5. 2024PoseCrafter: One-Shot Personalized Video Synthesis Following Flexible Pose Controlcited by 10
  6. 2023UnitedHuman: Harnessing Multi-Source Data for High-Resolution Human Generationcited by 9
  7. 2024TED-VITON: Transformer-Empowered Diffusion Models for Virtual Try-Oncited by 8
  8. 2023ViscoNet: Bridging and Harmonizing Visual and Textual Conditioning for ControlNetcited by 7
  9. 2022Collecting The Puzzle Pieces: Disentangled Self-Driven Human Pose Transfer by Permuting Texturescited by 6
  10. 2024DiffBody: Diffusion-based Pose and Shape Editing of Human Imagescited by 6
  11. 2025MF-VITON: High-Fidelity Mask-Free Virtual Try-On with Minimal Inputcited by 6
  12. 2025Multi-focal Conditioned Latent Diffusion for Person Image Synthesiscited by 6
  13. 2022VGFlow: Visibility guided Flow Network for Human Reposingcited by 5
  14. 2023Total Selfie: Generating Full-Body Selfiescited by 5
  15. 2023ConditionVideo: Training-Free Condition-Guided Text-to-Video Generationcited by 5
  16. 2025Rethink Sparse Signals for Pose-guided Text-to-image Generationcited by 5
  17. 2023Disentangled Representation Learning for Controllable Person Image Generationcited by 4
  18. 2023Open-World Pose Transfer via Sequential Test-Time Adaptioncited by 3
  19. 2025Enhanced Multi-Scale Cross-Attention for Person Image Generationcited by 3
  20. 2023RePoseDM: Recurrent Pose Alignment and Gradient Guidance for Pose Guided Image Synthesiscited by 2
  21. 2024Independently Keypoint Learning for Small Object Semantic Correspondencecited by 2
  22. 2024One-Shot Learning for Pose-Guided Person Image Synthesis in the Wildcited by 2
  23. 2022UMFuse: Unified Multi View Fusion for Human Editing applicationscited by 1
  24. 2024FAMOUS: High-Fidelity Monocular 3D Human Digitization Using View Synthesiscited by 1
  25. 2025CanKD: Cross-Attention-based Non-local operation for Feature-based Knowledge Distillationcited by 1
  26. 2026DAC-Pose: Dual-Agent Collaborative Framework for Pose-Guided Human Generationcited by 1
  27. 2023One-Shot Stylization for Full-Body Human Imagescited by 0
  28. 2024Direct May Not Be the Best: An Incremental Evolution View of Pose Generationcited by 0
  29. 2024Structure-Aware Human Body Reshaping with Adaptive Affinity-Graph Networkcited by 0
  30. 2024Fusion Embedding for Pose-Guided Person Image Synthesis with Diffusion Modelcited by 0
  31. 2024DRDM: A Disentangled Representations Diffusion Model for Synthesizing Realistic Person Imagescited by 0
  32. 2025Jointly Conditioned Diffusion Model for Multi-View Pose-Guided Person Image Synthesiscited by 0
  33. 2026PoseCraft: Tokenized 3D Body Landmark and Camera Conditioning for Photorealistic Human Image Synthesiscited by 0