We present a learning‐based approach for virtual try‐on applications based on a fully convolutional graph neural network. In contrast to existing data‐driven models, which are trained for a specific ...garment or mesh topology, our fully convolutional model can cope with a large family of garments, represented as parametric predefined 2D panels with arbitrary mesh topology, including long dresses, shirts, and tight tops. Under the hood, our novel geometric deep learning approach learns to drape 3D garments by decoupling the three different sources of deformations that condition the fit of clothing: garment type, target body shape, and material. Specifically, we first learn a regressor that predicts the 3D drape of the input parametric garment when worn by a mean body shape. Then, after a mesh topology optimization step where we generate a sufficient level of detail for the input garment type, we further deform the mesh to reproduce deformations caused by the target body shape. Finally, we predict fine‐scale details such as wrinkles that depend mostly on the garment material. We qualitatively and quantitatively demonstrate that our fully convolutional approach outperforms existing methods in terms of generalization capabilities and memory requirements, and therefore it opens the door to more general learning‐based models for virtual try‐on applications.
A similarity measure for illustration style Garces, Elena; Agarwala, Aseem; Gutierrez, Diego ...
ACM transactions on graphics,
07/2014, Volume:
33, Issue:
4
Journal Article
Peer reviewed
This paper presents a method for measuring the similarity in style between two pieces of vector art, independent of content. Similarity is measured by the differences between four types of features: ...color, shading, texture, and stroke. Feature weightings are learned from crowdsourced experiments. This perceptual similarity enables style-based search. Using our style-based search feature, we demonstrate an application that allows users to create stylistically-coherent clip art mash-ups.
Intrinsic video and applications Ye, Genzhi; Garces, Elena; Liu, Yebin ...
ACM transactions on graphics,
07/2014, Volume:
33, Issue:
4
Journal Article
Peer reviewed
We present a method to decompose a
video
into its intrinsic components of reflectance and shading, plus a number of related example applications in video editing such as segmentation, stylization, ...material editing, recolorization and color transfer. Intrinsic decomposition is an ill-posed problem, which becomes even more challenging in the case of video due to the need for temporal coherence and the potentially large memory requirements of a global approach. Additionally, user interaction should be kept to a minimum in order to ensure efficiency. We propose a probabilistic approach, formulating a Bayesian Maximum a Posteriori problem to drive the propagation of clustered reflectance values from the first frame, and defining additional constraints as priors on the reflectance and shading. We explicitly leverage temporal information in the video by building a causal-anticausal, coarse-to-fine iterative scheme, and by relying on optical flow information. We impose no restrictions on the input video, and show examples representing a varied range of difficult cases. Our method is the first one designed explicitly for video; moreover, it naturally ensures temporal consistency, and compares favorably against the state of the art in this regard.
Utilizando diversas fuentes —como su diario personal cuando era una niña de once años en un colegio católico— y una amplia variedad de entrevistas a mujeres colombianas, Elena Garcés crea un análisis ...intelectual y erudito de las estructuras patriarcales sobre las cuales se basa la mayoría de las comunidades en el mundo. En Las mujeres colombianas, Garcés examina la cultura, la historia, la economía, las leyes y la religión en el país, al tiempo que promueve ideas que dilapidan la restricción forzada a la que se han visto sometidas las mujeres de esa sociedad. Con las historias de vida de dieciocho mujeres colombianas como punto de partida, la autora explora sus experiencias y sufrimientos en el contexto de la vida familiar y las instituciones sociales. Las mujeres colombianas es un importante estudio, ideal para estudiantes universitarios en los campos de estudios de la mujer, estudios latinoamericanos, religión, antropología y sociología.
We present a model to measure the similarity in appearance between different materials, which correlates with human similarity judgments. We first create a database of 9,000 rendered images depicting ...objects with varying materials, shape and illumination. We then gather data on perceived similarity from crowdsourced experiments; our analysis of over 114,840 answers suggests that indeed a shared perception of appearance similarity exists. We feed this data to a deep learning architecture with a novel loss function, which learns a feature space for materials that correlates with such perceived appearance similarity. Our evaluation shows that our model outperforms existing metrics. Last, we demonstrate several applications enabled by our metric, including appearance-based search for material suggestions, database visualization, clustering and summarization, and gamut mapping.
Decomposing an input image into its intrinsic shading and reflectance components is a long‐standing ill‐posed problem. We present a novel algorithm that requires no user strokes and works on a single ...image. Based on simple assumptions about its reflectance and luminance, we first find clusters of similar reflectance in the image, and build a linear system describing the connections and relations between them. Our assumptions are less restrictive than widely‐adopted Retinex‐based approaches, and can be further relaxed in conflicting situations. The resulting system is robust even in the presence of areas where our assumptions do not hold. We show a wide variety of results, including natural images, objects from the MIT dataset and texture images, along with several applications, proving the versatility of our method.
Phosphate is a key uremic toxin associated with adverse outcomes. As chronic kidney disease (CKD) progresses, the kidney capacity to excrete excess dietary phosphate decreases, triggering ...compensatory endocrine responses that drive CKD-mineral and bone disorder (CKD-MBD). Eventually, hyperphosphatemia develops, and low phosphate diet and phosphate binders are prescribed. Recent data have identified a potential role of the gut microbiota in mineral bone disorders. Thus, parathyroid hormone (PTH) only caused bone loss in mice whose microbiota was enriched in the Th17 cell-inducing taxa segmented filamentous bacteria. Furthermore, the microbiota was required for PTH to stimulate bone formation and increase bone mass, and this was dependent on bacterial production of the short-chain fatty acid butyrate. We review current knowledge on the relationship between phosphate, microbiota and CKD-MBD. Topics include microbial bioactive compounds of special interest in CKD, the impact of dietary phosphate and phosphate binders on the gut microbiota, the modulation of CKD-MBD by the microbiota and the potential therapeutic use of microbiota to treat CKD-MBD through the clinical translation of concepts from other fields of science such as the optimization of phosphorus utilization and the use of phosphate-accumulating organisms.
Givosiran for Acute Intermittent Porphyria Gomá-Garcés, Elena; Pérez-Gómez, M Vanessa; Ortíz, Alberto
The New England journal of medicine,
11/2020, Volume:
383, Issue:
20
Journal Article
Many high‐level image processing tasks require an estimate of the positions, directions and relative intensities of the light sources that illuminated the depicted scene. In image‐based rendering, ...augmented reality and computer vision, such tasks include matching image contents based on illumination, inserting rendered synthetic objects into a natural image, intrinsic images, shape from shading and image relighting. Yet, accurate and robust illumination estimation, particularly from a single image, is a highly ill‐posed problem. In this paper, we present a new method to estimate the illumination in a single image as a combination of achromatic lights with their 3D directions and relative intensities. In contrast to previous methods, we base our azimuth angle estimation on curve fitting and recursive refinement of the number of light sources. Similarly, we present a novel surface normal approximation using an osculating arc for the estimation of zenith angles. By means of a new data set of ground‐truth data and images, we demonstrate that our approach produces more robust and accurate results, and show its versatility through novel applications such as image compositing and analysis.
Many high‐level image processing tasks require an estimate of the positions, directions and relative intensities of the light sources that illuminated the depicted scene. In image‐based rendering, augmented reality and computer vision, such tasks include matching image contents based on illumination, inserting rendered synthetic objects into a natural image, intrinsic images, shape from shading and image relighting. Yet, accurate and robust illumination estimation, particularly from a single image, is a highly ill‐posed problem. In this paper, we present a new method to estimate the illumination in a single image as a combination of achromatic lights with their 3D directions and relative intensities. In contrast to previous methods, we base our azimuth angle estimation on curve fitting and recursive refinement of the number of light sources. Likewise, we present a novel surface normal approximation using an osculating arc for the estimation of zenith angles.
Background: CKD is a risk factor for severe COVID-19. However, the clinical spectrum of COVID-19 in hemodialysis patients is still poorly characterized. Objective: To analyze the clinical spectrum of ...COVID-19 on hemodialysis patients. Method: A retrospective observational study was conducted on 66 hemodialysis patients. Nasopharyngeal swab PCR and serology for SARS-CoV-2, blood analysis, chest radiography, treatment, and outcomes were assessed. Results: COVID-19 was diagnosed in 50 patients: 38 (76%) were PCR-positive and 12 (24%) were PCR-negative but developed anti-SARS-CoV-2 antibodies. By contrast, 17% of PCR-positive patients failed to develop detectable antibodies against SARS-CoV-2. Among PCR-positive patients, 5/38 (13%) were asymptomatic, while among PCR-negative patients 7/12 (58%) were asymptomatic (p = 0.005) for a total of 12/50 (24%) asymptomatic patients. No other differences were found between PCR-positive and PCR-negative patients. No differences in potential predisposing factors were found between asymptomatic and symptomatic patients except for a lower use of ACE inhibitors among asymptomatic patients. Asymptomatic patients had laboratory evidence of milder disease such as higher lymphocyte counts and oxygen saturation and lower troponin I and interleukin-6 levels than symptomatic patients. Overall mortality was 7/50 (14%) and occurred only in symptomatic PCR-positive patients in whom mortality was 7/33 (21%). Conclusions: Asymptomatic SARS-CoV-2 infection is common in hemodialysis patients, especially among patients with initial negative PCR that later seroconvert. Thus COVID-19 mortality in hemodialysis patients may be lower than previously estimated based on PCR tests alone.