3D Face Reconstruction with Deep Learning: Architectures, Datasets, and Benchmark Analysis
Sensors · 20.04.2026 · 26 (8) · 2540
DOI: 10.3390/s26082540 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 20.04.2026. Verfasst von Sankarshan Dasgupta und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, University of Dayton, Dayton, OH 45469, USA. Die Arbeit nennt 169 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Three-Dimensional (3D) face reconstruction from monocular Red-Green-Blue (RGB) imagery remains a fundamental yet ill-posed challenge in computer vision, with applications in biometrics, augmented reality/virtual reality (AR/VR), and intelligent visual sensing systems. While deep learning has significantly improved reconstruction fidelity and realism, existing surveys primarily focus on network architectures in isolation, often overlooking how sensing conditions, data acquisition protocols, and geometric calibration influence reconstruction reliability and evaluation outcomes. This paper presents a sensor-aware, end-to-end review of deep learning-based 3D face reconstruction and introduces a unified modular framework that connects sensing hardware, data acquisition, calibration, representation learning, and geometric refinement within a coherent pipeline. The reconstruction process is organized into four stages: sensor-driven acquisition and calibration, landmark estimation and feature extraction, 3D representation and parameter regression, and iterative refinement via differentiable rendering. Within this framework, we examine how sensor characteristics, calibration accuracy, representation models, and supervision strategies affect reconstruction accuracy, perceptual quality, robustness, and computational efficiency. We further synthesize the reported results across widely used benchmarks using both geometric and perceptual metrics, highlighting trade-offs between reconstruction fidelity and deployment constraints. By integrating sensing-aware analysis with architectural evaluation, this survey provides practical insights for developing scalable and reliable 3D face reconstruction systems under real-world conditions.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Science, University of Dayton, Dayton, OH 45469, USA.
ORCID-Profile: Sankarshan Dasgupta, Tam V Nguyen
Zitieren
APA
Dasgupta, S., Shen, J., & Nguyen, T. V. (2026). 3D Face Reconstruction with Deep Learning: Architectures, Datasets, and Benchmark Analysis. Sensors, 26(8), 2540. https://doi.org/10.3390/s26082540
Vancouver
Dasgupta S, Shen J, Nguyen TV. 3D Face Reconstruction with Deep Learning: Architectures, Datasets, and Benchmark Analysis. Sensors. 2026;26(8):2540. doi:10.3390/s26082540
BibTeX
@article{Dasgupta2026,
author = {Dasgupta, Sankarshan and Shen, Ju and Nguyen, Tam V},
title = {3D Face Reconstruction with Deep Learning: Architectures, Datasets, and Benchmark Analysis},
journal = {Sensors},
year = {2026},
volume = {26},
number = {8},
pages = {2540},
doi = {10.3390/s26082540}
}
EUVIMED