Neural Modeling of Portrait Bas-Relief From a Single Photograph.

In this paper, we present an end-to-end neural solution to model portrait bas-relief from a single photograph, which is cast as a problem of image-to-depth translation. The main challenge is the lack of bas-relief data for network training. To solve this problem, we propose a semi-automatic pipeline to synthesize bas-relief samples. The main idea is to first construct normal maps from photos, and then generate bas-relief samples by reconstructing pixel-wise depths. In total, our synthetic dataset contains 23 k pixel-wise photo/bas-relief pairs. Since the process of bas-relief synthesis requires a certain amount of user interactions, we propose end-to-end solutions with various network architectures, and train them on the synthetic data. We select the one that gave the best results through qualitative and quantitative comparisons. Experiments on numerous portrait photos, comparisons with state-of-the-art methods and evaluations by artists have proven the effectiveness and efficiency of the selected network.

Mean Scar Entropy by Late Gadolinium Enhancement Cardiac Magnetic Resonance Is Associated With Ventricular Arrhythmias Events in Hypertrophic Cardiomyopathy.

Background: Ventricular arrhythmias are associated with sudden cardiac death (SCD) in hypertrophic cardiomyopathy (HCM). Previous studies have found the late gadolinium enhancement (LGE) on cardiac magnetic resonance (CMR) was independently associated with ventricular arrhythmia (VA) in HCM. The risk stratification of VA remains complex and LGE is present in the majority of HCM patients. This study was conducted to determine whether the scar heterogeneity from LGE-derived entropy is associated with the VAs in HCM patients. Materials and Methods: Sixty-eight HCM patients with scarring were retrospectively enrolled and divided into VA (31 patients) and non-VA (37 patients) groups. The left ventricular ejection fraction (LVEF) and percentage of the LGE (% LGE) were evaluated. The scar heterogeneity was quantified by the entropy within the scar and left ventricular (LV) myocardium. Results: Multivariate analyses showed that a higher scar [hazard ratio (HR) 2.682; 95% CI: 1.022-7.037; p = 0.039] was independently associated with VA, after the adjustment for the LVEF, %LGE, LV maximal wall thickness (MWT), and left atrium (LA) diameter. Conclusion: Scar entropy and %LGE are both independent risk indicators of VA. A high scar entropy may indicate an arrhythmogenic scar, an identification of which may have value for the clinical status assessment of VAs in HCM patients.

Portrait Relief Modeling from a Single Image.

We present a novel solution to enable portrait relief modeling from a single image. The main challenges are geometry reconstruction, facial details recovery and depth structure preservation. Previous image-based methods are developed for portrait bas-relief modeling in 2.5D form, but not adequate for 3D-like high relief modeling with undercut features. In this paper, we propose a template-based framework to generate portrait reliefs of various forms. Our method benefits from Shape-from-Shading (SFS). Specifically, we use bi-Laplacian mesh deformation to guide the relief modeling. Given a portrait image, we first use a template face to fit the portrait. We then apply bi-Laplacian mesh deformation to align the facial features. Afterwards, SFS-based reconstruction with a few user interactions is used to optimize the face depth, and create a relief with similar appearance to the input. Both depth structures and geometric details can be well constructed in the final relief. Experiments and comparisons to other methods demonstrate the effectiveness of the proposed method.

Bas-Relief Modeling from Normal Images with Intuitive Styles.

Traditional 3D model-based bas-relief modeling methods are often limited to model-dependent and monotonic relief styles. This paper presents a novel method for digital bas-relief modeling with intuitive style control. Given a composite normal image, the problem discussed in this paper involves generating a discontinuity-free depth field with high compression of depth data while preserving or even enhancing fine details. In our framework, several layers of normal images are composed into a single normal image. The original normal image on each layer is usually generated from 3D models or through other techniques as described in this paper. The bas-relief style is controlled by choosing a parameter and setting a targeted height for them. Bas-relief modeling and stylization are achieved simultaneously by solving a sparse linear system. Different from previous work, our method can be used to freely design bas-reliefs in normal image space instead of in object space, which makes it possible to use any popular image editing tools for bas-relief modeling. Experiments with a wide range of 3D models and scenes show that our method can effectively generate digital bas-reliefs.