Download PDF

Reconstructing 3D clothed human avatars from single images is a challenging task, especially when encountering complex poses and loose clothing. Current methods exhibit limitations in performance, largely attributable to their dependence on insufficient 2D image features and inconsistent query methods. Owing to this, we present the Global-correlated 3D-decoupling Transformer for clothed Avatar reconstruction (GTA), a novel transformer-based architecture that reconstructs clothed human avatars from monocular images. Our approach leverages transformer architectures by utilizing a Vision Transformer model as an encoder for capturing global-correlated image features. Subsequently, our innovative 3D-decoupling decoder employs cross-attention to decouple tri-plane features, using learnable embeddings as queries for cross-plane generation. To effectively enhance feature fusion with the tri-plane 3D feature and human body prior, we propose a hybrid prior fusion strategy combining spatial and prior-enhanced queries, leveraging the benefits of spatial localization and human body prior knowledge. Comprehensive experiments on CAPE and THuman2.0 datasets illustrate that our method outperforms state-of-the-art approaches in both geometry and texture reconstruction, exhibiting high robustness to challenging poses and loose clothing, and producing higher-resolution textures. Codes will be available at this https URL.

Submission history

From: Zechuan Zhang [view email]
[v1] Sun, 24 Sep 2023 02:10:25 UTC (17,150 KB)
[v2] Tue, 26 Sep 2023 13:18:20 UTC (17,150 KB)
[v3] Mon, 23 Oct 2023 11:42:33 UTC (41,474 KB)

||||I|||| Skip to main content We gratefully acknowledge support from the Simons Foundation, member institutions , and all contributors. Donate > cs > arXiv:2309.13524v1 Help | Advanced Search All fields Title Author Abstract Comments Journal reference ACM classification MSC classification Report number arXiv identifier DOI ORCID arXiv author ID Help pages Full text Search GO quick links * Login * Help Pages * About Computer Science > Computer Vision and Pattern Recognition arXiv:2309.13524v1 (cs) [Submitted on 24 Sep 2023 (this version), latest version 23 Oct 2023 (v3)] Title: Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction Authors: Zechuan Zhang, Li Sun, Zongxin Yang, Ling Chen, Yi Yang Download a PDF of the paper titled Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction, by Zechuan Zhang and 4 other authors Download PDF Abstract: Reconstructing 3D clothed human avatars from single images is a challenging task, especially when encountering complex poses and loose clothing. Current methods exhibit limitations in performance, largely attributable to their dependence on insufficient 2D image features and inconsistent query methods. Owing to this, we present the Global-correlated 3D-decoupling Transformer for clothed Avatar reconstruction (GTA), a novel transformer-based architecture that reconstructs clothed human avatars from monocular images. Our approach leverages transformer architectures by utilizing a Vision Transformer model as an encoder for capturing global-correlated image features. Subsequently, our innovative 3D-decoupling decoder employs cross-attention to decouple tri-plane features, using learnable embeddings as queries for cross-plane generation. To effectively enhance feature fusion with the tri-plane 3D feature and human body prior, we propose a hybrid prior fusion strategy combining spatial and prior-enhanced queries, leveraging the benefits of spatial localization and human body prior knowledge. Comprehensive experiments on CAPE and THuman2.0 datasets illustrate that our method outperforms state-of-the-art approaches in both geometry and texture reconstruction, exhibiting high robustness to challenging poses and loose clothing, and producing higher-resolution textures. Codes will be available at this https URL. Comments: Accepted to NeurIPS 2023 Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2309.13524 [cs.CV] (or arXiv:2309.13524v1 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2309.13524 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Zechuan Zhang [view email] [v1] Sun, 24 Sep 2023 02:10:25 UTC (17,150 KB) [v2] Tue, 26 Sep 2023 13:18:20 UTC (17,150 KB) [v3] Mon, 23 Oct 2023 11:42:33 UTC (41,474 KB) Full-text links: Access Paper: Download a PDF of the paper titled Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction, by Zechuan Zhang and 4 other authors * Download PDF * PostScript * Other Formats (view license) Current browse context: cs.CV < prev | next > new | recent | 2309 Change to browse by: cs cs.AI References & Citations * NASA ADS * Google Scholar * Semantic Scholar a export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) Links to Code Toggle Papers with Code (What is Papers with Code?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Core recommender toggle CORE Recommender (What is CORE?) About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?) * About * Help * Click here to contact arXiv Contact * Click here to subscribe Subscribe * Copyright * Privacy Policy * Web Accessibility Assistance * arXiv Operational Status Get status notifications via email or slack

Search across your past Websets

Research Papers: deep learning, transformer, anthropometric measurements

Search Criteria

Enrichments

Find more results