mlsanityData to 14 Oct 2026

Pose-dIVE: Pose-Diversified Augmentation with Diffusion Model for Person Re-Identification

arXiv 2406.16042 ↗First posted 23 Jun 2024cs.CVcited by 6

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

Person re-identification (Re-ID) often faces challenges due to variations in human poses and camera viewpoints, which significantly affect the appearance of individuals across images. Existing datasets frequently lack diversity and scalability in these aspects, hindering the generalization of Re-ID models to new camera systems or environments. To overcome this, we propose Pose-dIVE, a novel data augmentation approach that incorporates sparse and underrepresented human pose and camera viewpoint examples into the training data, addressing the limited diversity in the original training data distribution. Our objective is to augment the training dataset to enable existing Re-ID models to learn features unbiased by human pose and camera viewpoint variations. By conditioning the diffusion model on both the human pose and camera viewpoint through the SMPL model, our framework generates augmented training data with diverse human poses and camera viewpoints. Experimental results demonstrate the effectiveness of our method in addressing human pose bias and enhancing the generalizability of Re-ID models compared to other data augmentation-based Re-ID approaches.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 52 of its 81 references that are in the map. First posted on arXiv 23 Jun 2024.

Builds on

52 of 81 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion12 Apr
  2. 2022Person Image Synthesis via Denoising Diffusion Model22 Nov

Other references · 50

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  6. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  7. 2020Denoising Diffusion Implicit Modelscited by 9,781
  8. 2022Generative Adversarial Networkscited by 5,627
  9. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  10. 2017Random Erasing Data Augmentationcited by 1,239
  11. 2023Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animationcited by 688
  12. 2021Vector-quantized Image Modeling with Improved VQGANcited by 658
38 more
  1. 2020Deep Learning for Person Re-identification: A Survey and Outlookcited by 549
  2. 2017Person Transfer GAN to Bridge Domain Gap for Person Re-Identificationcited by 480
  3. 2021TransReID: Transformer-based Object Re-Identificationcited by 435
  4. 2018Everybody Dance Nowcited by 315
  5. 2017Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitrocited by 281
  6. 2019Joint Discriminative and Generative Learning for Person Re-identificationcited by 213
  7. 2016Person Re-identification: Past, Present and Futurecited by 181
  8. 2022CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labelscited by 181
  9. 2019A Strong Baseline and Batch Normalization Neck for Deep Person Re-identificationcited by 155
  10. 2019DwNet: Dense warp-based network for pose-guided human video generationcited by 115
  11. 2021Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identificationcited by 114
  12. 2023Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Taskscited by 96
  13. 2020Unsupervised Pre-training for Person Re-identificationcited by 95
  14. 2020XingGAN for Person Image Generationcited by 81
  15. 2017A Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Rankingcited by 74
  16. 2018FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identificationcited by 71
  17. 2017Pose-Normalized Image Generation for Person Re-identificationcited by 70
  18. 2017Camera Style Adaptation for Person Re-identificationcited by 68
  19. 2021Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformercited by 68
  20. 2022Exploring Dual-task Correlation for Pose Guided Person Image Generationcited by 68
  21. 2016SIFT Meets CNN: A Decade Survey of Instance Retrievalcited by 67
  22. 2022Body Part-Based Representation Learning for Occluded Person Re-Identificationcited by 64
  23. 2020Joint Generative and Contrastive Learning for Unsupervised Person Re-identificationcited by 58
  24. 2019Semantics-Aligned Representation Learning for Person Re-identificationcited by 51
  25. 2021AAformer: Auto-Aligned Transformer for Person Re-Identificationcited by 48
  26. 2018Batch DropBlock Network for Person Re-identification and Beyondcited by 45
  27. 2018Spatial-Temporal Person Re-identificationcited by 45
  28. 2021On the Unreasonable Effectiveness of Centroids in Image Retrievalcited by 45
  29. 2021Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning Methodcited by 42
  30. 2017Person Re-Identification by Camera Correlation Aware Feature Augmentationcited by 35
  31. 2023Learning Clothing and Pose Invariant 3D Shape Representation for Long-Term Person Re-Identificationcited by 34
  32. 2020Multi-task Learning with Coarse Priors for Robust Part-aware Person Re-identificationcited by 23
  33. 2019Unsupervised Person Re-identification by Deep Asymmetric Metric Embeddingcited by 22
  34. 2021FlipReID: Closing the Gap between Training and Inference in Person Re-Identificationcited by 16
  35. 2023MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReIDcited by 16
  36. 2021Learning to Disentangle Scenes for Person Re-identificationcited by 10
  37. 2023Learning Invariance from Generated Variance for Unsupervised Person Re-identificationcited by 7
  38. 2021Pose Invariant Person Re-Identification using Robust Pose-transformation GANcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2025SD-ReID: View-aware Stable Diffusion for Aerial-Ground Person Re-Identificationcited by 7
  2. 20263D-LENS: A 3D Lifting-based Elevated Novel-view Synthesis method for Single-View Aerial-Ground Re-Identificationcited by 2
  3. 2025An Empirical Study of Validating Synthetic Data for Text-Based Person Retrievalcited by 1
  4. 2026ID-Sim: An Identity-Focused Similarity Metriccited by 1
  5. 2026ReSAGE-PAR: Representational Similarity Assessment for Generative Expansion in Pedestrian Attribute Recognitioncited by 0
  6. 20263D-VITAL: Visibility-aware Identity Training from Artificial Liftings of 3D Reconstruction model for Cross-View Object Re-Identificationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-Training
  2. 2025Unleashing the Potential of Pre-Trained Diffusion Models for Generalizable Person Re-Identification
  3. 2021Semi-Supervised Domain Generalizable Person Re-Identification
  4. 2025Diffusion-based Synthetic Data Generation for Visible-Infrared Person Re-Identification
  5. 2024DLCR: A Generative Data Expansion Framework via Diffusion for Clothes-Changing Person Re-ID
  6. 2025ChatReID: Open-ended Interactive Person Retrieval via Hierarchical Progressive Tuning for Vision Language Models
  7. 2026A Generative AI Integrated Multimodal Framework for Low-Latency Multi-Camera Person Re-Identification
  8. 2025Causality and "In-the-Wild" Video-Based Person Re-ID: A Survey