mlsanityData to 14 Oct 2026

Combining Attention with Flow for Person Image Synthesis

arXiv 2108.01823 ↗First posted 4 Aug 2021cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Pose-guided person image synthesis aims to synthesize person images by transforming reference images into target poses. In this paper, we observe that the commonly used spatial transformation blocks have complementary advantages. We propose a novel model by combining the attention operation with the flow-based operation. Our model not only takes the advantage of the attention operation to generate accurate target structures but also uses the flow-based operation to sample realistic source textures. Both objective and subjective experiments demonstrate the superiority of our model. Meanwhile, comprehensive ablation studies verify our hypotheses and show the efficacy of the proposed modules. Besides, additional experiments on the portrait image editing task demonstrate the versatility of the proposed combination.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 30 of its 39 references that are in the map. First posted on arXiv 4 Aug 2021.

Builds on

30 of 39 references.

References · 30

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  4. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  5. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  6. 2016Improved Techniques for Training GANscited by 2,970
  7. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  8. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  9. 2017Non-local Neural Networkscited by 2,293
  10. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,039
  11. 2018Self-Attention Generative Adversarial Networkscited by 809
  12. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
18 more
  1. 2017VoxCeleb: a large-scale speaker identification datasetcited by 732
  2. 2019Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Setcited by 482
  3. 2017Pose Guided Person Image Generationcited by 251
  4. 2019Few-Shot Unsupervised Image-to-Image Translationcited by 222
  5. 2019Few-shot Video-to-Video Synthesiscited by 197
  6. 2017Deformable GANs for Pose-based Human Image Generationcited by 166
  7. 2019Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesiscited by 161
  8. 2020Controllable Person Image Synthesis with Attribute-Decomposed GANcited by 150
  9. 2019Progressive Pose Attention Transfer for Person Image Generationcited by 138
  10. 2018A Variational U-Net for Conditional Appearance and Shape Generationcited by 124
  11. 2020Cross-domain Correspondence Learning for Exemplar-based Image Translationcited by 116
  12. 2019DwNet: Dense warp-based network for pose-guided human video generationcited by 115
  13. 2019Dense Intrinsic Appearance Flow for Human Pose Transfercited by 104
  14. 2020Deep Image Spatial Transformation for Person Image Generationcited by 100
  15. 2017Disentangled Person Image Generationcited by 98
  16. 2021PISE: Person Image Synthesis and Editing with Decoupled GANcited by 62
  17. 2019Multi-mapping Image-to-Image Translation via Learning Disentanglementcited by 35
  18. 2021Structure-aware Person Image Generation with Pose Decomposition and Semantic Correlationcited by 11

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 4; 2024: 2; 2025: 1.

9 papers.

  1. 2023Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Modelscited by 104
  2. 2022Single Stage Virtual Try-on via Deformable Attention Flowscited by 65
  3. 2022Neural Texture Extraction and Distribution for Controllable Person Image Synthesiscited by 55
  4. 2023Human MotionFormer: Transferring Human Motions with Vision Transformerscited by 14
  5. 2023UniHuman: A Unified Model for Editing Human Images in the Wildcited by 12
  6. 2024Pose-Guided Fine-Grained Sign Language Video Generationcited by 8
  7. 2025Multi-focal Conditioned Latent Diffusion for Person Image Synthesiscited by 6
  8. 2023RePoseDM: Recurrent Pose Alignment and Gradient Guidance for Pose Guided Image Synthesiscited by 2
  9. 2024Beyond Imperfections: A Conditional Inpainting Approach for End-to-End Artifact Removal in VTON and Pose Transfercited by 0