1 code implementation • 28 Nov 2023 • Jesus Zarzar, Bernard Ghanem
We present a novel approach for digitizing real-world objects by estimating their geometry, material properties, and environmental lighting from a set of posed images with fixed lighting.
no code implementations • 15 Jun 2023 • Juan C. Pérez, Sara Rojas, Jesus Zarzar, Bernard Ghanem
We found that introducing image augmentations during training presents challenges such as geometric and photometric inconsistencies for learning NRMs from images.
1 code implementation • ICCV 2023 • Sara Rojas, Jesus Zarzar, Juan Camilo Perez, Artsiom Sanakoyeu, Ali Thabet, Albert Pumarola, Bernard Ghanem
Re-ReND is designed to achieve real-time performance by converting the NeRF into a representation that can be efficiently processed by standard graphics pipelines.
no code implementations • 21 Nov 2022 • Jesus Zarzar, Sara Rojas, Silvio Giancola, Bernard Ghanem
The predicted semantic fields allow SegNeRF to achieve an average mIoU of $\textbf{30. 30%}$ for 2D novel view segmentation, and $\textbf{37. 46%}$ for 3D part segmentation, boasting competitive performance against point-based methods by using only a few posed images.
no code implementations • 27 Nov 2019 • Jesus Zarzar, Silvio Giancola, Bernard Ghanem
We integrate residual GCNs in a two-stage 3D object detection pipeline, where 3D object proposals are refined using a novel graph representation.
Ranked #14 on 3D Object Detection on KITTI Cars Hard
no code implementations • 25 Mar 2019 • Jesus Zarzar, Silvio Giancola, Bernard Ghanem
Successively, we refine our selection of 3D object candidates by exploiting the similarity capability of a 3D Siamese network.
1 code implementation • CVPR 2019 • Silvio Giancola, Jesus Zarzar, Bernard Ghanem
We design a Siamese tracker that encodes model and candidate shapes into a compact latent representation.