mlsanityData to 7 Oct 2026

Revisiting the Role of Texture in 3D Person Re-identification

arXiv 2410.00348 ↗First posted 1 Oct 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

This study introduces a new framework for 3D person re-identification (re-ID) that leverages readily available high-resolution texture data in 3D reconstruction to improve the performance and explainability of the person re-ID task. We propose a method to emphasize texture in 3D person re-ID models by incorporating UVTexture mapping, which better differentiates human subjects. Our approach uniquely combines UVTexture and its heatmaps with 3D models to visualize and explain the person re-ID process. In particular, the visualization and explanation are achieved through activation maps and attribute-based attention maps, which highlight the important regions and features contributing to the person re-ID decision. Our contributions include: (1) a novel technique for emphasizing texture in 3D models using UVTexture processing, (2) an innovative method for explicating person re-ID matches through a combination of 3D models and UVTexture mapping, and (3) achieving state-of-the-art performance in 3D person re-ID. We ensure the reproducibility of our results by making all data, codes, and models publicly available.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 51 of its 59 references that are in the map. First posted on arXiv 1 Oct 2024.

Builds on

51 of 59 references.

References · 51

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2016Densely Connected Convolutional Networkscited by 6,691
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  7. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  9. 2017Random Erasing Data Augmentationcited by 1,235
  10. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  11. 2017End-to-end Recovery of Human Shape and Posecited by 883
  12. 2016Performance Measures and a Data Set for Multi-Target, Multi-Camera Trackingcited by 685
38 more
  1. 2017Person Transfer GAN to Bridge Domain Gap for Person Re-Identificationcited by 479
  2. 2021TransReID: Transformer-based Object Re-Identificationcited by 432
  3. 2019Omni-Scale Feature Learning for Person Re-Identificationcited by 292
  4. 2018Learning Discriminative Features with Multiple Granularities for Person Re-Identificationcited by 290
  5. 2017Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitrocited by 280
  6. 2017Re-ranking Person Re-identification with k-reciprocal Encodingcited by 260
  7. 2019Joint Discriminative and Generative Learning for Person Re-identificationcited by 211
  8. 2022ECON: Explicit Clothed humans Optimized via Normal integrationcited by 199
  9. 2019ABD-Net: Attentive but Diverse Person Re-Identificationcited by 126
  10. 2019Relation-Aware Global Attention for Person Re-identificationcited by 124
  11. 2021Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformercited by 119
  12. 2022Clothes-Changing Person Re-identification with RGB Modality Onlycited by 98
  13. 2017Improving Person Re-identification by Attribute and Identity Learningcited by 95
  14. 2023Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Taskscited by 94
  15. 2018Interpreting CNNs via Decision Treescited by 89
  16. 2018Dissecting Person Re-identification from the Viewpoint of Viewpointcited by 83
  17. 2021Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformercited by 68
  18. 2022Body Part-Based Representation Learning for Occluded Person Re-Identificationcited by 63
  19. 20193DPeople: Modeling the Geometry of Dressed Humanscited by 58
  20. 2020Joint Generative and Contrastive Learning for Unsupervised Person Re-identificationcited by 57
  21. 2018Spatial-Temporal Person Re-identificationcited by 45
  22. 2021Feature Erasing and Diffusion Network for Occluded Person Re-Identificationcited by 41
  23. 20213D Human Texture Estimation from a Single Image with Transformerscited by 35
  24. 2023Learning Clothing and Pose Invariant 3D Shape Representation for Long-Term Person Re-Identificationcited by 34
  25. 2020Parameter-Efficient Person Re-identification in the 3D Spacecited by 33
  26. 2022Dynamic Prototype Mask for Occluded Person Re-Identificationcited by 30
  27. 20213D Human Pose, Shape and Texture from Low-Resolution Images and Videoscited by 26
  28. 2021Explainable Person Re-Identification with Attribute-guided Metric Distillationcited by 23
  29. 2018Explaining Neural Networks Semantically and Quantitativelycited by 20
  30. 2022The State of Aerial Surveillance: A Surveycited by 20
  31. 2021Person Re-Identification with a Locally Aware Transformercited by 19
  32. 2024AG-ReID.v2: Bridging Aerial and Ground Views for Person Re-identificationcited by 19
  33. 2023Aerial-Ground Person Re-IDcited by 18
  34. 2022Cloning Outfits from Real-World Images to 3D Characters for Generalizable Person Re-Identificationcited by 17
  35. 2018Video-based Person Re-identification via 3D Convolutional Networks and Non-local Attentioncited by 14
  36. 2023TranSG: Transformer-Based Skeleton Graph Prototype Contrastive Learning with Structure-Trajectory Prompted Reconstruction for Person Re-Identificationcited by 14
  37. 2021Pose-driven Attention-guided Image Generation for Person Re-Identificationcited by 11
  38. 2022Transformer Based Multi-Grained Features for Unsupervised Person Re-Identificationcited by 6

50 most cited of 51 All 51 (JSON)

Built on by

Not cited yet.