Implicit Shape and Appearance Priors for Few-Shot Full Head Reconstruction
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-05 · 47 (5) · 3691-3705
DOI: 10.1109/tpami.2025.3540542 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-05. Verfasst von Pol Caselles und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 77 Literaturangaben.
Abstract (Originalsprache)
Recent advancements in learning techniques that employ coordinate-based neural representations have yielded remarkable results in multi-view 3D reconstruction tasks. However, these approaches often require a substantial number of input views (typically several tens) and computationally intensive optimization procedures to achieve their effectiveness. In this paper, we address these limitations specifically for the problem of few-shot full 3D head reconstruction. We accomplish this by incorporating a probabilistic shape and appearance prior into coordinate-based representations, enabling faster convergence and improved generalization when working with only a few input images (even as low as a single image). During testing, we leverage this prior to guiding the fitting process of a signed distance function using a differentiable renderer. By incorporating the statistical prior alongside parallelizable ray tracing and dynamic caching strategies, we achieve an efficient and accurate approach to few-shot full 3D head reconstruction. Moreover, we extend the H3DS dataset, which now comprises 60 high-resolution 3D full-head scans and their corresponding posed images and masks, which we use for evaluation purposes. By leveraging this dataset, we demonstrate the remarkable capabilities of our approach in achieving state-of-the-art results in geometry reconstruction while being an order of magnitude faster than previous approaches.
Zitieren
APA
Caselles, P., Ramon, E., Garcia, J., Triginer, G., & Moreno-Noguer, F. (2025). Implicit Shape and Appearance Priors for Few-Shot Full Head Reconstruction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(5), 3691-3705. https://doi.org/10.1109/tpami.2025.3540542
Vancouver
Caselles P, Ramon E, Garcia J, Triginer G, Moreno-Noguer F. Implicit Shape and Appearance Priors for Few-Shot Full Head Reconstruction. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(5):3691-3705. doi:10.1109/tpami.2025.3540542
BibTeX
@article{Caselles2025,
author = {Caselles, Pol and Ramon, Eduard and Garcia, Jaime and Triginer, Gil and Moreno-Noguer, Francesc},
title = {Implicit Shape and Appearance Priors for Few-Shot Full Head Reconstruction},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2025},
volume = {47},
number = {5},
pages = {3691--3705},
doi = {10.1109/tpami.2025.3540542}
}
EUVIMED