mlsanityData to 7 Oct 2026

Multi-scale Attention Guided Pose Transfer

arXiv 2202.06777 ↗First posted 14 Feb 2022cs.CV cs.MMcited by 10

Not on the map. Why?

Abstract (arXiv)

Pose transfer refers to the probabilistic image generation of a person with a previously unseen novel pose from another image of that person having a different pose. Due to potential academic and commercial applications, this problem is extensively studied in recent years. Among the various approaches to the problem, attention guided progressive generation is shown to produce state-of-the-art results in most cases. In this paper, we present an improved network architecture for pose transfer by introducing attention links at every resolution level of the encoder and decoder. By utilizing such dense multi-scale attention guided approach, we are able to achieve significant improvement over the existing methods both visually and analytically. We conclude our findings with extensive qualitative and quantitative comparisons against several existing methods on the DeepFashion dataset.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 38 of its 57 references that are in the map. First posted on arXiv 14 Feb 2022.

Builds on

38 of 57 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  6. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  7. 2014Going Deeper with Convolutionscited by 4,231
  8. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  9. 2016Improved Techniques for Training GANscited by 2,938
  10. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  11. 2014Conditional Generative Adversarial Netscited by 2,152
  12. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
26 more
  1. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  2. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  3. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  4. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  5. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
  6. 2017VITON: An Image-based Virtual Try-on Networkcited by 285
  7. 2017Pose Guided Person Image Generationcited by 251
  8. 2018Toward Characteristic-Preserving Image-based Virtual Try-On Networkcited by 192
  9. 2017Deformable GANs for Pose-based Human Image Generationcited by 166
  10. 2016Semantic Image Inpainting with Deep Generative Modelscited by 156
  11. 2019Progressive Pose Attention Transfer for Person Image Generationcited by 138
  12. 2018A Variational U-Net for Conditional Appearance and Shape Generationcited by 124
  13. 2017Disentangled Person Image Generationcited by 98
  14. 2018Synthesizing Images of Humans in Unseen Posescited by 96
  15. 2020XingGAN for Person Image Generationcited by 81
  16. 2016Scribbler: Controlling Deep Image Synthesis with Sketch and Colorcited by 77
  17. 2018Unsupervised Person Image Synthesis in Arbitrary Posescited by 55
  18. 2019STEFANN: Scene Text Editor using Font Adaptive Neural Networkcited by 46
  19. 2017A Generative Model of People in Clothingcited by 37
  20. 2020Bipartite Graph Reasoning GANs for Person Image Generationcited by 34
  21. 2017Multi-View Image Generation from a Single-Viewcited by 27
  22. 2020PoNA: Pose-guided Non-local Attention for Human Pose Transfercited by 20
  23. 2021Pose-driven Attention-guided Image Generation for Person Re-Identificationcited by 11
  24. 2019Toward Learning a Unified Many-to-Many Mapping for Diverse Image Translationcited by 10
  25. 2020Wish You Were Here: Context-Aware Human Generationcited by 10
  26. 2019Efficient Deep Neural Network for Photo-realistic Image Super-Resolutioncited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 2; 2024: 2; 2025: 3; 2026: 1.

10 papers.

  1. 2024TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Modelscited by 18
  2. 2022TIPS: Text-Induced Pose Synthesiscited by 11
  3. 2023FASTER: A Font-Agnostic Scene Text Editing and Rendering Frameworkcited by 6
  4. 2022Scene Aware Person Image Generation through Global Contextual Conditioningcited by 3
  5. 2025Enhanced Multi-Scale Cross-Attention for Person Image Generationcited by 3
  6. 2025Synthetic Human Action Video Data Generation with Pose Transfercited by 2
  7. 2025Can Pose Transfer Models Generate Realistic Human Motion?cited by 1
  8. 2023Semantically Consistent Person Image Generationcited by 0
  9. 2024Direct May Not Be the Best: An Incremental Evolution View of Pose Generationcited by 0
  10. 2026AlignVTOFF: Texture-Spatial Feature Alignment for High-Fidelity Virtual Try-Offcited by 0