1 code implementation • 19 Mar 2024 • Carlos Rodriguez-Pardo, Dan Casas, Elena Garces, Jorge Lopez-Moreno
We introduce TexTile, a novel differentiable metric to quantify the degree upon which a texture image can be concatenated with itself without introducing repeating artifacts (i. e., the tileability).
1 code implementation • Computer Graphics Forum 2023 • Carlos Rodriguez-Pardo, Javier Fabre, Elena Garces, Jorge Lopez-Moreno
We propose NEnv, a deep-learning fully-differentiable method, capable of compressing and learning to sample from a single environment map.
no code implementations • 3 Jul 2023 • Carlos Rodriguez-Pardo, Konstantinos Kazatzis, Jorge Lopez-Moreno, Elena Garces
However, existing neural materials are immutable, meaning that their output for a certain query of UVs, camera, and light vector is fixed once they are trained.
no code implementations • CVPR 2023 • Carlos Rodriguez-Pardo, Henar Dominguez-Elvira, David Pascual-Hernandez, Elena Garces
We showcase the performance of our method with a real dataset of digitized textile materials and show that a commodity flatbed scanner can produce the type of diffuse illumination required as input to our method.
no code implementations • 13 Apr 2023 • Carlos Rodriguez-Pardo, Melania Prieto-Martin, Dan Casas, Elena Garces
We propose a method to estimate the mechanical parameters of fabrics using a casual capture setup with a depth camera.
no code implementations • 13 Jan 2022 • Carlos Rodriguez-Pardo, Elena Garces
We present SeamlessGAN, a method capable of automatically generating tileable texture maps from a single input exemplar.
no code implementations • 7 Dec 2021 • Elena Garces, Carlos Rodriguez-Pardo, Dan Casas, Jorge Lopez-Moreno
Intrinsic imaging or intrinsic image decomposition has traditionally been described as the problem of decomposing an image into two layers: a reflectance, the albedo invariant color of the material; and a shading, produced by the interaction between light and geometry.
no code implementations • 5 Dec 2021 • Carlos Rodriguez-Pardo, Elena Garces
Our model relies on a supervised image-to-image translation framework and is agnostic to the transferred domain; we showcase a semantic segmentation, a normal map, and a stylization.