1 code implementation • 12 Oct 2023 • Pol Caselles, Eduard Ramon, Jaime Garcia, Gil Triginer, Francesc Moreno-Noguer
Recent advancements in learning techniques that employ coordinate-based neural representations have yielded remarkable results in multi-view 3D reconstruction tasks.
no code implementations • 7 Sep 2022 • Pol Caselles, Eduard Ramon, Jaime Garcia, Xavier Giro-i-Nieto, Francesc Moreno-Noguer, Gil Triginer
Our key ingredients are two data-driven statistical models based on neural fields that resolve the ambiguities of single-view 3D surface reconstruction and appearance factorization.
1 code implementation • ICCV 2021 • Eduard Ramon, Gil Triginer, Janna Escur, Albert Pumarola, Jaime Garcia, Xavier Giro-i-Nieto, Francesc Moreno-Noguer
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).