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

• URL: http://arxiv.org/abs/2308.10658v3
• Date: Thu, 21 Sep 2023 04:23:54 GMT
• Title: Learning Clothing and Pose Invariant 3D Shape Representation for Long-Term Person Re-Identification
• Authors: Feng Liu, Minchul Kim, ZiAng Gu, Anil Jain, Xiaoming Liu
• Abstract summary: We aim to extend LT-ReID beyond pedestrian recognition to include a wider range of real-world human activities. This setting poses additional challenges due to the geometric misalignment and appearance ambiguity caused by the diversity of human pose and clothing. We propose a new approach 3DInvarReID for disentangling identity from non-identity components.
• Score: 16.797826602710035
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Content and Salient Semantics Collaboration for Cloth-Changing Person Re-Identification [74.10897798660314]
  Cloth-changing person Re-IDentification aims at recognizing the same person with clothing changes across non-overlapping cameras. We propose the Content and Salient Semantics Collaboration framework, facilitating cross-parallel semantics interaction and refinement. Our framework is simple yet effective, and the vital design is the Semantics Mining and Refinement (SMR) module.
  arXiv  Detail & Related papers  (2024-05-26T15:17:28Z)
• Exploring Shape Embedding for Cloth-Changing Person Re-Identification via 2D-3D Correspondences [9.487097819140653]
  We propose a new shape embedding paradigm for cloth-changing ReID. The shape embedding paradigm based on 2D-3D correspondences remarkably enhances the model's global understanding of human body shape. To promote the study of ReID under clothing change, we construct 3D Dense Persons (DP3D), which is the first large-scale cloth-changing ReID dataset.
  arXiv  Detail & Related papers  (2023-10-27T19:26:30Z)
• Identity-Guided Collaborative Learning for Cloth-Changing Person Reidentification [29.200286257496714]
  We propose a novel identity-guided collaborative learning scheme (IGCL) for cloth-changing person ReID. First, we design a novel clothing attention stream to reasonably reduce the interference caused by clothing information. Second, we propose a human semantic attention and body jigsaw stream to highlight the human semantic information and simulate different poses of the same identity. Third, a pedestrian identity enhancement stream is further proposed to enhance the identity importance and extract more favorable identity robust features.
  arXiv  Detail & Related papers  (2023-04-10T06:05:54Z)
• Gait Recognition Using 3-D Human Body Shape Inference [22.385670309906352]
  We present the usage of inferring 3-D body shapes distilled from limited images. We provide a method for learning 3-D body inference from silhouettes by transferring knowledge from 3-D shape prior to RGB photos.
  arXiv  Detail & Related papers  (2022-12-18T09:27:00Z)
• gDNA: Towards Generative Detailed Neural Avatars [94.9804106939663]
  We show that our model is able to generate natural human avatars wearing diverse and detailed clothing. Our method can be used on the task of fitting human models to raw scans, outperforming the previous state-of-the-art.
  arXiv  Detail & Related papers  (2022-01-11T18:46:38Z)
• The Power of Points for Modeling Humans in Clothing [60.00557674969284]
  Currently it requires an artist to create 3D human avatars with realistic clothing that can move naturally. We show that a 3D representation can capture varied topology at high resolution and that can be learned from data. We train a neural network with a novel local clothing geometric feature to represent the shape of different outfits.
  arXiv  Detail & Related papers  (2021-09-02T17:58:45Z)
• Multigranular Visual-Semantic Embedding for Cloth-Changing Person Re-identification [38.7806002518266]
  This work proposes a novel visual-semantic embedding algorithm (MVSE) for cloth-changing person ReID. To fully represent a person with clothing changes, a multigranular feature representation scheme (MGR) is employed, and then a cloth desensitization network (CDN) is designed. A partially semantically aligned network (PSA) is proposed to obtain the visual-semantic information that is used to align the human attributes.
  arXiv  Detail & Related papers  (2021-08-10T09:14:44Z)
• Apparel-invariant Feature Learning for Apparel-changed Person Re-identification [70.16040194572406]
  Most public ReID datasets are collected in a short time window in which persons' appearance rarely changes. In real-world applications such as in a shopping mall, the same person's clothing may change, and different persons may wearing similar clothes. It is critical to learn an apparel-invariant person representation under cases like cloth changing or several persons wearing similar clothes.
  arXiv  Detail & Related papers  (2020-08-14T03:49:14Z)
• Long-Term Cloth-Changing Person Re-identification [154.57752691285046]
  Person re-identification (Re-ID) aims to match a target person across camera views at different locations and times. Existing Re-ID studies focus on the short-term cloth-consistent setting, under which a person re-appears in different camera views with the same outfit. In this work, we focus on a much more difficult yet practical setting where person matching is conducted over long-duration, e.g., over days and months.
  arXiv  Detail & Related papers  (2020-05-26T11:27:21Z)
• Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Images [50.34202789543989]
  Deep Fashion3D is the largest collection to date of 3D garment models. It provides rich annotations including 3D feature lines, 3D body pose and the corresponded multi-view real images. A novel adaptable template is proposed to enable the learning of all types of clothing in a single network.
  arXiv  Detail & Related papers  (2020-03-28T09:20:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.