Publication

Implicit shape and appearance priors for few-shot full head reconstruction

Journal Article (2025)

Journal

IEEE Transactions on Pattern Analysis and Machine Intelligence

Pages

3691-3705

Volume

47

Number

5

Doc link

https://doi.org/10.1109/TPAMI.2025.3540542

File

Download the digital copy of the doc pdf document

Authors

Projects associated

Abstract

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.

Categories

pattern recognition.

Author keywords

Neural Radiance Field, Signed Distance Function, Few-shot 3D Reconstruction

Scientific reference

P. Caselles, E. Ramon, J. Garcia, G. Triginer and F. Moreno-Noguer. Implicit shape and appearance priors for few-shot full head reconstruction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(5): 3691-3705, 2025.