Fig. 1. Visualizations under natural lighting of four captured 1k resolution SVBRDFs estimated using our deep inverse rendering framework. The leather material (left) is reconstructed from just 2 input photographs captured with a mobile phone camera and flash, while the other materials are recovered from 20 input photographs. In this paper we present a unified deep inverse rendering framework for estimating the spatially-varying appearance properties of a planar exemplar from an arbitrary number of input photographs, ranging from just a single photograph to many photographs. The precision of the estimated appearance scales from plausible when the input photographs fails to capture all the reflectance information, to accurate for large input sets. A key distinguishing feature of our framework is that it directly optimizes for the appearance parameters in a latent embedded space of spatially-varying appearance, such that no handcrafted heuristics are needed to regularize the optimization. This latent embedding is learned through a fully convolutional auto-encoder that has been designed to regularize the optimization. Our framework not only supports an arbitrary number of input photographs, but also at high

Figure 1: Affinity-based edit propagation methods such as allow one to change the appearance of an image or video (e.g., the color of the bird here) using only a few strokes, yet consuming prohibitive amount of time and memory for large data (e.g., 48 minutes and 23GB for this video containing 61M pixels). Our approximation scheme drastically reduces the cost of edit propagation methods (to 8 seconds and 22MB in this example) by exploring adaptive clustering in the affinity space. Video courtesy of BBC Motion Gallery (UK). AbstractImage/video editing by strokes has become increasingly popular due to the ease of interaction. Propagating the user inputs to the rest of the image/video, however, is often time and memory consuming especially for large data. We propose here an efficient scheme that allows affinity-based edit propagation to be computed on data containing tens of millions of pixels at interactive rate (in matter of seconds). The key in our scheme is a novel means for approximately solving the optimization problem involved in edit propagation, using adaptive clustering in a high-dimensional, affinity space. Our approximation significantly reduces the cost of existing affinitybased propagation methods while maintaining visual fidelity, and enables interactive stroke-based editing even on high resolution images and long video sequences using commodity computers.

Abstract This study aimed to determine the mutational spectrum of familial Parkinson’s disease and sporadic early-onset Parkinson’s disease (sEOPD) in a mainland Chinese population and the clinical features of mutation carriers. We performed multiplex ligation-dependent probe amplification assays and whole-exome sequencing for 1676 unrelated patients with Parkinson’s disease in a mainland Chinese population, including 192 probands from families with autosomal-recessive Parkinson’s disease, 242 probands from families with autosomal-dominant Parkinson’s disease, and 1242 sEOPD patients (age at onset ≤ 50). According to standards and guidelines from the American College of Medical Genetics and Genomics, pathogenic/likely pathogenic variants in 23 known Parkinson’s disease-associated genes occurred more frequently in the autosomal-recessive Parkinson’s disease cohort (65 of 192, 33.85%) than in the autosomal-dominant Parkinson’s disease cohort (10 of 242, 4.13%) and the sEOPD cohort (57 of 1242, 4.59%), which leads to an overall molecular diagnostic yield of 7.88% (132 of 1676). We found that PRKN was the most frequently mutated gene (n = 83, 4.95%) and present the first evidence of an SNCA duplication and LRRK2 p.N1437D variant in mainland China. In addition, several novel pathogenic/likely pathogenic variants including LRRK2 (p.V1447M and p.Y1645S), ATP13A2 (p.R735X and p.A819D), FBXO7 (p.G67E), LRP10 (c.322dupC/p.G109Rfs*51) and TMEM230 (c.429delT/p.P144Qfs*2) were identified in our cohort. Furthermore, the age at onset of the 132 probands with genetic diagnoses (median, 31.5 years) was about 14.5 years earlier than that of patients without molecular diagnoses (i.e. non-carriers, median 46.0 years). Specifically, the age at onset of Parkinson’s disease patients with pathogenic/likely pathogenic variants in ATP13A2, PLA2G6, PRKN, or PINK1 was significantly lower than that of non-carriers, while the age at onset of carriers with other gene pathogenic/likely pathogenic variants was similar to that of non-carriers. The clinical spectrum of Parkinson’s disease-associated gene carriers in this mainland Chinese population was similar to that of other populations. We also detected 61 probands with GBA possibly pathogenic variants (3.64%) and 59 probands with GBA p.L444P (3.52%). These results shed insight into the genetic spectrum and clinical manifestations of Parkinson’s disease in mainland China and expand the existing repertoire of pathogenic or likely pathogenic variants involved in known Parkinson’s disease-associated genes. Our data highlight the importance of genetic testing in Parkinson’s disease patients with age at onset < 40 years, especially in those from families with a recessive inheritance pattern, who may benefit from early diagnosis and treatment.

No abstract

Figure 1: Affinity-based edit propagation methods such as allow one to change the appearance of an image or video (e.g., the color of the bird here) using only a few strokes, yet consuming prohibitive amount of time and memory for large data (e.g., 48 minutes and 23GB for this video containing 61M pixels). Our approximation scheme drastically reduces the cost of edit propagation methods (to 8 seconds and 22MB in this example) by exploring adaptive clustering in the affinity space. Video courtesy of BBC Motion Gallery (UK). AbstractImage/video editing by strokes has become increasingly popular due to the ease of interaction. Propagating the user inputs to the rest of the image/video, however, is often time and memory consuming especially for large data. We propose here an efficient scheme that allows affinity-based edit propagation to be computed on data containing tens of millions of pixels at interactive rate (in matter of seconds). The key in our scheme is a novel means for approximately solving the optimization problem involved in edit propagation, using adaptive clustering in a high-dimensional, affinity space. Our approximation significantly reduces the cost of existing affinitybased propagation methods while maintaining visual fidelity, and enables interactive stroke-based editing even on high resolution images and long video sequences using commodity computers.

including regression-based and learning-based methods, have been explored to achieve better rendering quality with less computational cost. However, most of these methods rely on handcrafted optimization objectives, which lead to artifacts such as blurs and unfaithful details. In this paper, we present an adversarial approach for denoising Monte Carlo rendering. Our key insight is that generative adversarial networks can help denoiser networks to produce more realistic high-frequency details and global illumination by learning the distribution from a set of high-quality Monte Carlo path tracing images. We also adapt a novel feature modulation method to utilize auxiliary features better, including normal, albedo and depth. Compared to previous state-of-the-art methods, our approach produces a better reconstruction of the Monte Carlo integral from a few samples, performs more robustly at different sample rates, and takes only a second for megapixel images.

1 SG, 9.2%, 180 fps 3 SGs, 6.0% , 76 fps 5 SGs, 3.4 %, 55 fps 7 SGs, 2.0% , 36 fps 9 SGs, 1.1% , 27 fps 1 ASG 11 SGs, 0.54% , 22 fps 13 SGs, 0.26% , 19 fps 15 SGs, 0.11% , 17 fps 1 ASG, 0.10% , 125 fps reference Figure 1: Comparison of the SG (Spherical Gaussian) based approximation with the ASG (Anisotropic Spherical Gaussian) based approximation in rendering a highly anisotropic metal dish, under an environment light and two local lights. The BRDF of the metal dish is approximated by different number of ASGs or SGs in different images. Notice the superior property of ASGs over SGs. The result generated by 1 ASG already matches the path-traced reference well (with a L 2 error of 0.10%), and achieves a high framerate of 125 fps, while, to achieve a similar quality, more than 10 SGs are required, but with much lower framerates (19 fps for 13 SGs or 17 fps for 15 SGs). The L 2 error and the framerates for each configuration are also given in the corresponding subtitle. AbstractWe present a novel anisotropic Spherical Gaussian (ASG) function, built upon the Bingham distribution [Bingham 1974], which is much more effective and efficient in representing anisotropic spherical functions than Spherical Gaussians (SGs). In addition to retaining many desired properties of SGs, ASGs are also rotationally invariant and capable of representing all-frequency signals. To further strengthen the properties of ASGs, we have derived approximate closed-form solutions for their integral, product and convolution operators, whose errors are nearly negligible, as validated by quantitative analysis. Supported by all these operators, ASGs can be adapted in existing SG-based applications to enhance their scalability in handling anisotropic effects. To demonstrate the accuracy and efficiency of ASGs in practice, we have applied ASGs in two important SG-based rendering applications and the experimental results clearly reveal the merits of ASGs.

No abstract