Carlos Rodríguez - Pardo

Politecnico di Milano | Polimi · Department of Management, Economics and Industrial Engineering DIG

We propose a method to estimate the mechanical parameters of fabrics using a casual capture setup with a depth camera. Our approach enables to create mechanically‐correct digital representations of real‐world textile materials, which is a fundamental step for many interactive design and engineering applications. As opposed to existing capture metho...

We propose a learning-based method to recover normals, specularity, and roughness from a single diffuse image of a material, using microgeometry appearance as our primary cue. Previous methods that work on single images tend to produce over-smooth outputs with artifacts, operate at limited resolution, or train one model per class with little room f...

Neural material representations are becoming a popular way to represent materials for rendering. They are more expressive than analytic models and occupy less memory than tabulated BTFs. 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. Wh...

Environment maps are commonly used to represent and compute far‐field illumination in virtual scenes. However, they are expensive to evaluate and sample from, limiting their applicability to real‐time rendering. Previous methods have focused on compression through spherical‐domain approximations, or on learning priors for natural, day‐light illumin...

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). Existing methods for tileable texture synthesis focus on general texture quality, but lack explicit analysis of the intrinsic repeatability properties...

Existing devices for measuring material appearance in spatially-varying samples are limited to a single scale, either micro or mesoscopic. This is a practical limitation when the material has a complex multi-scale structure. In this paper, we present a system and methods to digitize materials at two scales, designed to include high-resolution data...

Neural material representations are becoming a popular way to represent materials for rendering. They are more expressive than analytic models and occupy less memory than tabulated BTFs. 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. Wh...

We propose a learning-based method to recover normals, specularity, and roughness from a single diffuse image of a material, using microgeometry appearance as our primary cue. Previous methods that work on single images tend to produce over-smooth outputs with artifacts, operate at limited resolution, or train one model per class with little room f...

We propose a method to estimate the mechanical parameters of fabrics using a casual capture setup with a depth camera. Our approach enables to create mechanically-correct digital representations of real-world textile materials, which is a fundamental step for many interactive design and engineering applications. As opposed to existing capture metho...

The unprecedented growth in the amount and variety of data we can store about the behaviour of customers has been parallel to the popularization and development of machine learning algorithms. This confluence of factors has created the opportunity of understanding customer behaviour and preferences in ways that were undreamt of in the past. In this...

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. Deep learning techniques have been broadly applied in recent years to increase t...

Real-time graphics applications require high-quality textured materials to convey realism in virtual environments. Generating these textures is challenging as they need to be visually realistic, seamlessly tileable, and have a small impact on the memory consumption of the application. For this reason, they are often created manually by skilled arti...

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. Deep learning techniques have been broadly applied in recent years to increase t...

We present a deep learning-based method for propagating spatially-varying visual material attributes (e.g. texture maps or image stylizations) to larger samples of the same or similar materials. For training, we leverage images of the material taken under multiple illuminations and a dedicated data augmentation policy, making the transfer robust to...

The unprecedented growth in the amount and variety of data we can store about the behaviour of customers has been parallel to the popularization and development of machine learning algorithms. This confluence of factors has created the opportunity of understanding customer behaviour and preferences in ways that were undreamt of in the past. In this...

Textures made of regular repeating patterns are ubiquitous in the real world, most notably in man-made environments. They are defined by the presence of a repeating element, which can show a significant amount of random variations, non-rigid deformations or color noise. We propose an end-to-end pipeline capable of finding the size of the minimal re...

The use of computational methods to evaluate aesthetics in photography has gained interest in recent years due to the popularization of convolutional neural networks and the availability of new annotated datasets. Most studies in this area have focused on designing models that do not take into account individual preferences for the prediction of th...

Textures made of regular repeating patterns are ubiquitous in the real world, most notably in man-made environments. They are defined by the presence of a repeating element, which can show a significant amount of random variations, non-rigid deformations or color noise. We propose an end-to-end pipeline capable of finding the size of the minimal re...

The use of computational methods to evaluate aesthetics in photography has gained interest in recent years due to the popularization of convolutional neural networks and the availability of new annotated datasets. Most studies in this area have focused on designing models that do not take into account individual preferences for the prediction of th...

The new technologies for data analysis, such as decision tree learning, may help to predict the risk of developing diseases. The aim of the present work was to develop a pilot decision tree learning to predict overweight/obesity based on the combination of six single nucleotide polymorphisms (SNP) located in feeding-associated genes. Genotype study...

We propose a transfer-learning method capable of surpassing the state-of-the-art results in predicting personalised preferences in aesthetics in photography, while eliminating the need for data about the contents and styles of the pictures. Our methodology allows the creation of end-to-end user-specific aesthetic prediction models with a smaller se...

Data analysis is comprised of a set of processes that allows a key support for making better decisions. The ability to analyse data in the field of retail trade allows companies to obtain valuable information such as understanding the profile of customers who demand a particular type of product, optimizing the price of certain products, identifying...

This work has been developed within the project of Applied Artificial Intelligence Group at UC3M, called ”Augmented Science”, in order to disseminate and support education in science through Augmented Reality (AR) tools. The project is part of new developments provided with AR systems on mobile devices and their application in promoting science tea...