EUVIMEDEUVIMED entdecken
Crossref

MinD-3D++: Advancing fMRI-Based 3D Reconstruction With High-Quality Textured Mesh Generation and a Comprehensive Dataset

Jianxiong Gao, Yanwei Fu, Yuqian Fu, Yun Wang, Xuelin Qian, Jianfeng Feng

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025

DOI: 10.1109/tpami.2025.3599860 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025. Verfasst von Jianxiong Gao und 5 weiteren Autor:innen. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Imaging, Three-Dimensional. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 52 Literaturangaben. Gefördert von: STI 2030-Major Projects.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reconstructing 3D visuals from functional Magnetic Resonance Imaging (fMRI) data, introduced as Recon3DMind, is of significant interest to both cognitive neuroscience and computer vision. To advance this task, we present the fMRI-3D dataset, which includes data from 15 participants and showcases a total of 4,768 3D objects. The dataset consists of two components: fMRI-Shape, previously introduced and available at https://huggingface.co/datasets/Fudan-fMRI/fMRI-Shape, and fMRI-Objaverse, proposed in this paper and available at https://huggingface.co/datasets/Fudan-fMRI/fMRI-Objaverse. fMRI-Objaverse includes data from 5 subjects, 4 of whom are also part of the core set in fMRI-Shape. Each subject views 3,142 3D objects across 117 categories, all accompanied by text captions. This significantly enhances the diversity and potential applications of the dataset. Moreover, we propose MinD-3D++, a novel framework for decoding textured 3D visual information from fMRI signals. The framework evaluates the feasibility of not only reconstructing 3D objects from the human mind but also generating, for the first time, 3D textured meshes with detailed textures from fMRI data. We establish new benchmarks by designing metrics at the semantic, structural, and textured levels to evaluate model performance. Furthermore, we assess the model's effectiveness in out-of-distribution settings and analyze the attribution of the proposed 3D pari fMRI dataset in visual regions of interest (ROIs) in fMRI signals. Our experiments demonstrate that MinD-3D++ not only reconstructs 3D objects with high semantic and spatial accuracy but also provides deeper insights into how the human brain processes 3D visual information.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingImaging, Three-DimensionalHumansBrainAlgorithmsAdultFemaleMaleDatabases, Factual

Förderung

  • STI 2030-Major Projects

Zitieren

APA

Gao, J., Fu, Y., Fu, Y., Wang, Y., Qian, X., & Feng, J. (2025). MinD-3D++: Advancing fMRI-Based 3D Reconstruction With High-Quality Textured Mesh Generation and a Comprehensive Dataset. IEEE Transactions on Pattern Analysis and Machine Intelligence. https://doi.org/10.1109/tpami.2025.3599860

Vancouver

Gao J, Fu Y, Fu Y, Wang Y, Qian X, Feng J. MinD-3D++: Advancing fMRI-Based 3D Reconstruction With High-Quality Textured Mesh Generation and a Comprehensive Dataset. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025. doi:10.1109/tpami.2025.3599860

BibTeX
@article{Gao2025,
  author = {Gao, Jianxiong and Fu, Yanwei and Fu, Yuqian and Wang, Yun and Qian, Xuelin and Feng, Jianfeng},
  title = {MinD-3D++: Advancing fMRI-Based 3D Reconstruction With High-Quality Textured Mesh Generation and a Comprehensive Dataset},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  doi = {10.1109/tpami.2025.3599860}
}
Kostenlos starten →