mlsanityData to 14 Oct 2026

Learning Clothing and Pose Invariant 3D Shape Representation for Long-Term Person Re-Identification

arXiv 2308.10658 ↗First posted 21 Aug 2023cs.CVcited by 34

Not on the map. Why?

Abstract (arXiv)

Long-Term Person Re-Identification (LT-ReID) has become increasingly crucial in computer vision and biometrics. In this work, we aim to extend LT-ReID beyond pedestrian recognition to include a wider range of real-world human activities while still accounting for cloth-changing scenarios over large time gaps. This setting poses additional challenges due to the geometric misalignment and appearance ambiguity caused by the diversity of human pose and clothing. To address these challenges, we propose a new approach 3DInvarReID for (i) disentangling identity from non-identity components (pose, clothing shape, and texture) of 3D clothed humans, and (ii) reconstructing accurate 3D clothed body shapes and learning discriminative features of naked body shapes for person ReID in a joint manner. To better evaluate our study of LT-ReID, we collect a real-world dataset called CCDA, which contains a wide variety of human activities and clothing changes. Experimentally, we show the superior performance of our approach for person ReID.

Key facts. Cited by 34 papers in the map (data through 14 Oct 2026). Builds on 54 of its 67 references that are in the map. First posted on arXiv 21 Aug 2023.

Builds on

54 of 67 references.

References · 54

  1. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  2. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  3. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  4. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 786
  5. 2020Deep Learning for Person Re-identification: A Survey and Outlookcited by 549
  6. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  7. 2017Person Transfer GAN to Bridge Domain Gap for Person Re-Identificationcited by 480
  8. 2017Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)cited by 473
  9. 2018Learning Discriminative Features with Multiple Granularities for Person Re-Identificationcited by 291
  10. 2021ICON: Implicit Clothed humans Obtained from Normalscited by 283
  11. 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
  12. 2021SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapescited by 221
38 more
  1. 2020Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identificationcited by 215
  2. 2019Joint Discriminative and Generative Learning for Person Re-identificationcited by 213
  3. 2020Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-IDcited by 212
  4. 2018Harmonious Attention Network for Person Re-Identificationcited by 211
  5. 2019DeepHuman: 3D Human Reconstruction from a Single Imagecited by 182
  6. 2016Person Re-identification: Past, Present and Futurecited by 181
  7. 2021SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networkscited by 181
  8. 2021ARCH++: Animation-Ready Clothed Human Reconstruction Revisitedcited by 174
  9. 2021SMPLicit: Topology-aware Generative Model for Clothed Peoplecited by 155
  10. 2020TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Stylecited by 149
  11. 2022Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothingcited by 126
  12. 2020BCNet: Learning Body and Cloth Shape from A Single Imagecited by 120
  13. 2021Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothingcited by 102
  14. 2022Clothes-Changing Person Re-identification with RGB Modality Onlycited by 98
  15. 2020Person Re-identification by Contour Sketch under Moderate Clothing Changecited by 91
  16. 2018Part-Aligned Bilinear Representations for Person Re-identificationcited by 90
  17. 2021NPMs: Neural Parametric Models for 3D Deformable Shapescited by 90
  18. 2020AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-identificationcited by 81
  19. 2020Accurate 3D Hand Pose Estimation for Whole-Body 3D Human Mesh Estimationcited by 81
  20. 2016A Discriminatively Learned CNN Embedding for Person Re-identificationcited by 78
  21. 2021MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Imagescited by 78
  22. 2022gDNA: Towards Generative Detailed Neural Avatarscited by 72
  23. 2019Gait Recognition via Disentangled Representation Learningcited by 70
  24. 2021Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularizationcited by 69
  25. 2018Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identificationcited by 62
  26. 2018Multi-Level Factorisation Net for Person Re-Identificationcited by 58
  27. 2019Unsupervised Tracklet Person Re-Identificationcited by 55
  28. 2019Unsupervised Person Re-identification by Soft Multilabel Learningcited by 53
  29. 2021DoubleField: Bridging the Neural Surface and Radiance Fields for High-fidelity Human Reconstruction and Renderingcited by 52
  30. 2020When Person Re-identification Meets Changing Clothescited by 51
  31. 2022Accurate 3D Body Shape Regression using Metric and Semantic Attributescited by 50
  32. 2021Large-Scale Spatio-Temporal Person Re-identification: Algorithms and Benchmarkcited by 47
  33. 2018Unsupervised Person Re-identification by Deep Learning Tracklet Associationcited by 45
  34. 20223D Clothed Human Reconstruction in the Wildcited by 42
  35. 2022Learned Vertex Descent: A New Direction for 3D Human Model Fittingcited by 37
  36. 2020COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identificationcited by 35
  37. 2020Parameter-Efficient Person Re-identification in the 3D Spacecited by 33
  38. 2018Disentangling Features in 3D Face Shapes for Joint Face Reconstruction and Recognitioncited by 27

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 12; 2025: 13; 2026: 8.

34 papers.

Sort:

By area:

  1. 2024KeyPoint Relative Position Encoding for Face Recognitioncited by 38
  2. 2024A Versatile Framework for Multi-scene Person Re-identificationcited by 14
  3. 2025SapiensID: Foundation for Human Recognitioncited by 14
  4. 2024Open-Set Biometrics: Beyond Good Closed-Set Modelscited by 12
  5. 2025DIFFER: Disentangling Identity Features via Semantic Cues for Clothes-Changing Person Re-IDcited by 11
  6. 2025HAMoBE: Hierarchical and Adaptive Mixture of Biometric Experts for Video-based Person ReIDcited by 10
  7. 2024DLCR: A Generative Data Expansion Framework via Diffusion for Clothes-Changing Person Re-IDcited by 8
  8. 2025Identity-aware Feature Decoupling Learning for Clothing-change Person Re-identificationcited by 8
  9. 2023Whole-body Detection, Recognition and Identification at Altitude and Rangecited by 7
  10. 2024Pose-dIVE: Pose-Diversified Augmentation with Diffusion Model for Person Re-Identificationcited by 6
  11. 2024CCUP: A Controllable Synthetic Data Generation Pipeline for Pretraining Cloth-Changing Person Re-Identification Modelscited by 6
  12. 2025Beyond Role-Based Surgical Domain Modeling: Generalizable Re-Identification in the Operating Roomcited by 6
22 more
  1. 2025Colors See Colors Ignore: Clothes Changing ReID with Color Disentanglementcited by 6
  2. 2024Diversifying Human Pose in Synthetic Data for Aerial-view Human Detectioncited by 5
  3. 2025Coarse Attribute Prediction with Task Agnostic Distillation for Real World Clothes Changing ReIDcited by 5
  4. 2025Dissecting Human Body Representations in Deep Networks Trained for Person Identificationcited by 4
  5. 2025Generalizable Object Re-Identification via Visual In-Context Promptingcited by 4
  6. 2026FusionAgent: A Multimodal Agent with Dynamic Model Selection for Human Recognitioncited by 4
  7. 2024Clothes-Changing Person Re-Identification with Feasibility-Aware Intermediary Matchingcited by 2
  8. 2025Unconstrained Body Recognition at Altitude and Range: Comparing Four Approachescited by 2
  9. 2026From 3D Pose to Prose: Biomechanics-Grounded Vision--Language Coachingcited by 2
  10. 20263D-LENS: A 3D Lifting-based Elevated Novel-view Synthesis method for Single-View Aerial-Ground Re-Identificationcited by 2
  11. 2024Rethinking Clothes Changing Person ReID: Conflicts, Synthesis, and Optimizationcited by 1
  12. 2024Learning an Adaptive and View-Invariant Vision Transformer for Real-Time UAV Trackingcited by 1
  13. 2025PS-ReID: Advancing Person Re-Identification and Precise Segmentation with Multimodal Retrievalcited by 1
  14. 2025Person detection and re-identification in open-world settings of retail stores and public spacescited by 1
  15. 2026IDSelect: A RL-Based Cost-Aware Selection Agent for Video-based Multi-Modal Person Recognitioncited by 1
  16. 2026CMCC-ReID: Cross-Modality Clothing-Change Person Re-Identificationcited by 1
  17. 2026SapiensID 2.0: Aligning Human Recognition Foundation Models with Human Perceptioncited by 1
  18. 2024Revisiting the Role of Texture in 3D Person Re-identificationcited by 0
  19. 2024See What You Seek: Semantic Contextual Integration for Cloth-Changing Person Re-Identificationcited by 0
  20. 2025TSDW: A Tri-Stream Dynamic Weight Network for Cloth-Changing Person Re-Identificationcited by 0
  21. 2026Learning Instance-Adaptive Low-Rank Orthogonal Subspaces for Clothes-Changing Person Re-Identificationcited by 0
  22. 2026Reliability-Aware 3D Geometric Injection for Universal Person Re-identificationcited by 0