@conference {cRamonb, title = {H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction}, booktitle = {International Conference on Computer Vision (ICCV)}, year = {2021}, publisher = {IEEE/CVF}, organization = {IEEE/CVF}, address = {Virtual}, abstract = {

Recent learning approaches that implicitly represent surface geometry using coordinate-based neural representations have shown impressive results in the problem of multi-view 3D reconstruction. The effectiveness of these techniques is, however, subject to the availability of a large number (several tens) of input views of the scene, and computationally demanding optimizations. In this paper, we tackle these limitations for the specific problem of few-shot full 3D head reconstruction, by endowing coordinate-based representations with a probabilistic shape prior that enables faster convergence and better generalization when using few input images (down to three). First, we learn a shape model of 3D heads from thousands of incomplete raw scans using implicit representations. At test time, we jointly overfit two coordinate-based neural networks to the scene, one modeling the geometry and another estimating the surface radiance, using implicit differentiable rendering. We devise a two-stage optimization strategy in which the learned prior is used to initialize and constrain the geometry during an initial optimization phase. Then, the prior is unfrozen and fine-tuned to the scene. By doing this, we achieve high-fidelity head reconstructions, including hair and shoulders, and with a high level of detail that consistently outperforms both state-of-the-art 3D Morphable Models methods in the few-shot scenario, and non-parametric methods when large sets of views are available.

}, author = {Ramon, Eduard and Triginer, Gil and Escur, Janna and Pumarola, Albert and Garcia, Jaime and Xavier Gir{\'o}-i-Nieto and Moreno, Francesc} }