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 • 9 Aug 2023 • Antonio Canela, Pol Caselles, Ibrar Malik, Eduard Ramon, Jaime García, Jordi Sánchez-Riera, Gil Triginer, Francesc Moreno-Noguer
In order to speed up the reconstruction process, we propose a system that combines, for the first time, a voxel-grid neural field representation with a surface renderer.
no code implementations • CVPR 2023 • Qianli Feng, Raghudeep Gadde, Wentong Liao, Eduard Ramon, Aleix Martinez
We derive a method that yields highly accurate semantic segmentation maps without the use of any additional neural network, layers, manually annotated training data, or supervised training.
no code implementations • 3 Nov 2022 • Marcelo Sanchez, Gil Triginer, Coloma Ballester, Lara Raad, Eduard Ramon
In this work, we revisit a two-stage approach for retouching facial wrinkles and obtain results with unprecedented realism.
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).
1 code implementation • 16 Aug 2019 • Eduard Ramon, Guillermo Ruiz, Thomas Batard, Xavier Giró-i-Nieto
This work proposes novel hyperparameter-free losses for single view 3D reconstruction with morphable models (3DMM).