Robust Denoising using Feature and Color Information

We propose a method that robustly combines color and feature buffers to denoise Monte Carlo renderings. On one hand, feature buffers, such as per pixel normals, textures, or depth, are effective in determining denoising filters because features are highly correlated with rendered images. Filters based solely on features, however, are prone to blurring image details that are not well represented by the features. On the other hand, color buffers represent all details, but they may be less effective to determine filters because they are contaminated by the noise that is supposed to be removed. We propose to obtain filters using a combination of color and feature buffers in an NL‐means and cross‐bilateral filtering framework. We determine a robust weighting of colors and features using a SURE‐based error estimate. We show significant improvements in subjective and quantitative errors compared to the previous state‐of‐theart. We also demonstrate adaptive sampling and space‐time filtering for animations.     

Environment Mapping and Other Applications of World Projections

Various techniques have been developed that employ projections of the world as seen from a particular viewpoint. Blinn and Newell introduced reflection mapping for simulating mirror reflections on curved surfaces. Miller and Hoffman have presented a general illumination model based on environment mapping. World projections have also been used to model distant objects and to produce pictures with the fish-eye distortion required for Omnimax frames. This article proposes a uniform framework for representing and using world projections and argues that the best general-purpose representation is the is projection onto a cube. Surface shading and texture filtering are discussed in the context of environment mapping, and methods are presented for obtaining diffuse and specular surface illumination from prefiltered environment maps. Comparisons are made with ray tracing, noting that two problems with ray tracing?obtaining diffuse reflection and antialiasing specular reflection?can be handled effectively by environment mapping.     

Non‐Local Image Reconstruction for Efficient Computation of Synthetic Bidirectional Texture Functions

Visual prototyping of materials is relevant for many computer graphics applications. A large amount of modelling flexibility can be obtained by directly rendering micro‐geometry. While this is possible in principle, it is usually computationally expensive. Recently, bidirectional texture functions (BTFs) have become popular for efficient photorealistic rendering of surfaces. We propose an efficient system for the computation of synthetic BTFs using Monte Carlo path tracing of micro‐geometry. We observe that BTFs usually consist of many similar apparent bidirectional reflectance distribution functions. By exploiting structural similarity we can reduce rendering times by one order of magnitude. This is done in a process we call non‐local image reconstruction, which has been inspired by non‐local means filtering. Our results indicate that synthesizing BTFs is highly practical and may currently only take a few minutes for BTFs with 70 × 70 viewing and lighting directions and 128 × 128 pixels.     

Importance Point Projection for GPU‐based Final Gathering

We present a practical importance‐driven method for GPU‐based final gathering. We take as input a point cloud representing directly illuminated scene geometry; we then project and splat the points to microbuffers, which store each shading pixel's occluded radiance field. We select points for projection based on importance, defined as each point's estimated contribution to a shading pixel. For each selected point, we calculate its splat size adaptively based on its importance value. The main advantage of our method is that it's simple and fast, and provides the capability to incorporate additional importance factors such as glossy reflection paths. We also introduce an image‐space adaptive sampling method, which combines adaptive image subdivision with joint bilateral upsampling to robustly preserve fine details. We have implemented our algorithm on the GPU, providing high‐quality rendering for dynamic scenes at near interactive rates.     

Pixel History Linear Models for Real‐Time Temporal Filtering

We propose a new real‐time temporal filtering and antialiasing (AA) method for rasterization graphics pipelines. Our method is based on Pixel History Linear Models (PHLM), a new concept for modeling the history of pixel shading values over time using linear models. Based on PHLM, our method can predict per‐pixel variations of the shading function between consecutive frames. This combines temporal reprojection with per‐pixel shading predictions in order to provide temporally coherent shading, even in the presence of very noisy input images. Our method can address both spatial and temporal aliasing problems under a unique filtering framework that minimizes filtering error through a recursive least squares algorithm. We demonstrate our method working with a commercial deferred shading engine for rasterization and with our own OpenGL deferred shading renderer. We have implemented our method in GPU and it has shown significant reduction of temporal flicker in very challenging scenarios including foliage rendering, complex non‐linear camera motions, dynamic lighting, reflections, shadows and fine geometric details. Our approach, based on PHLM, avoids the creation of visible ghosting artifacts and it reduces the filtering overblur characteristic of temporal deflickering methods. At the same time, the results are comparable to state‐of‐the‐art real‐time filters in terms of temporal coherence.     

A Stationary SVBRDF Material Modeling Method Based on Discrete Microsurface

Microfacet theory is commonly used to build reflectance models for surfaces. While traditional microfacet‐based models assume that the distribution of a surface's microstructure is continuous, recent studies indicate that some surfaces with tiny, discrete and stochastic facets exhibit glittering visual effects, while some surfaces with structured features exhibit anisotropic specular reflection. Accordingly, this paper proposes an efficient and stationary method of surface material modeling to process both glittery and non‐glittery surfaces in a consistent way. Our method comprises two steps: in the preprocessing step, we take a fixed‐size sample normal map as input, then organize 4D microfacet trees in position and normal space for arbitrary‐sized surfaces; we also cluster microfacets into 4D K‐lobes via the adaptive k‐means method. In the rendering step, moreover, surface normals can be efficiently evaluated using pre‐clustered microfacets. Our method is able to efficiently render any structured, discrete and continuous micro‐surfaces using a precisely reconstructed surface NDF. Our method is both faster and uses less memory compared to the state‐of‐the‐art glittery surface modeling works.     

Specular Highlight Removal for Real‐world Images

Removing specular highlight in an image is a fundamental research problem in computer vision and computer graphics. While various methods have been proposed, they typically do not work well for real‐world images due to the presence of rich textures, complex materials, hard shadows, occlusions and color illumination, etc. In this paper, we present a novel specular highlight removal method for real‐world images. Our approach is based on two observations of the real‐world images: (i) the specular highlight is often small in size and sparse in distribution; (ii) the remaining diffuse image can be represented by linear combination of a small number of basis colors with the sparse encoding coefficients. Based on the two observations, we design an optimization framework for simultaneously estimating the diffuse and specular highlight images from a single image. Specifically, we recover the diffuse components of those regions with specular highlight by encouraging the encoding coefficients sparseness using L₀ norm. Moreover, the encoding coefficients and specular highlight are also subject to the non‐negativity according to the additive color mixing theory and the illumination definition, respectively. Extensive experiments have been performed on a variety of images to validate the effectiveness of the proposed method and its superiority over the previous methods.     

The Metric Space of Ordered Weighted Average Operators with Distance Based on Accumulated Entries

Ordered weighted average (OWA) operators with their weighting vectors are very important in many applications. We show that directly taking Minkowski distances (including Manhattan distance and Euclidean distance) as the distances for any two OWA operator is not reasonable. In this study, we propose the standard distance measures for any two OWA operators and then propose a standard metric space for the set of all n‐dimension OWA operators. We analyze and discuss some properties of the introduced OWA metric and further propose a metric space of Choquet integrals represented by the underlying fuzzy measures. Some applications in decision making of OWA distances are also presented in this study.     

Learning Explicit Smoothing Kernels for Joint Image Filtering

Smoothing noises while preserving strong edges in images is an important problem in image processing. Image smoothing filters can be either explicit (based on local weighted average) or implicit (based on global optimization). Implicit methods are usually time‐consuming and cannot be applied to joint image filtering tasks, i.e., leveraging the structural information of a guidance image to filter a target image. Previous deep learning based image smoothing filters are all implicit and unavailable for joint filtering. In this paper, we propose to learn explicit guidance feature maps as well as offset maps from the guidance image and smoothing parameter that can be utilized to smooth the input itself or to filter images in other target domains. We design a deep convolutional neural network consisting of a fully‐convolution block for guidance and offset maps extraction together with a stacked spatially varying deformable convolution block for joint image filtering. Our models can approximate several representative image smoothing filters with high accuracy comparable to state‐of‐the‐art methods, and serve as general tools for other joint image filtering tasks, such as color interpolation, depth map upsampling, saliency map upsampling, flash/non‐flash image denoising and RGB/NIR image denoising.     

Interactive Glossy Reflections using GPU‐based Ray Tracing with Adaptive LOD

We present an interactive GPU‐based algorithm for accurately rendering high‐quality, dynamic glossy reflection effects from both HDR environment maps and local scene objects. Our method uses hardware rasterization to produce primary pixels, and GPU‐based BRDF importance sampling [ [CK07] ] to quickly generate reflected rays. We utilize a fast GPU ray tracer proposed by Carr et al. [ [CHCH06] ] to compute reflection hits. Our main contribution is an adaptive level‐of‐detail (LOD) control algorithm that greatly improves ray tracing performance during reflection shading. Specifically, we use the solid angle represented by each reflected ray to adaptively pick the level of termination in the BVH traversal step during ray tracing. This leads to 2 ～ 3x speedup over an unmodified implementation of [ [CHCH06] ]. Based on the same solid angle measure, we derive a texture filtering formula to reduce reflection aliasing artifacts, taking advantage of hardware MIP mapping. This extends the filtering algorithm presented in [ [CK07] ] from environment mapping to local scene reflection. Using our algorithm, we demonstrate interactive rendering rates for several scenes featuring dynamic lighting and material changes, spatially varying BRDF parameters, and rigid‐body object movement.     

基于相似性判断的双边滤波改进算法

双边滤波的浮点指数运算不利于算法的硬件实现。为此,提出一种基于相似性判断的改进型双边滤波算法。对滤波窗口内的像素进行亮度相似性判断,像素若满足相似条件则参与滤波,并采用倒数函数取代指数函数进行滤波。实验结果表明,改进的双边滤波算法可以均衡细节区域和平坦区域的降噪,且易于硬件实现,峰值信噪比相比双边滤波算法平均提高0．27dB。     

Path‐space Motion Estimation and Decomposition for Robust Animation Filtering

Renderings of animation sequences with physics‐based Monte Carlo light transport simulations are exceedingly costly to generate frame‐by‐frame, yet much of this computation is highly redundant due to the strong coherence in space, time and among samples. A promising approach pursued in prior work entails subsampling the sequence in space, time, and number of samples, followed by image‐based spatio‐temporal upsampling and denoising. These methods can provide significant performance gains, though major issues remain: firstly, in a multiple scattering simulation, the final pixel color is the composite of many different light transport phenomena, and this conflicting information causes artifacts in image‐based methods. Secondly, motion vectors are needed to establish correspondence between the pixels in different frames, but it is unclear how to obtain them for most kinds of light paths (e.g. an object seen through a curved glass panel). To reduce these ambiguities, we propose a general decomposition framework, where the final pixel color is separated into components corresponding to disjoint subsets of the space of light paths. Each component is accompanied by motion vectors and other auxiliary features such as reflectance and surface normals. The motion vectors of specular paths are computed using a temporal extension of manifold exploration and the remaining components use a specialized variant of optical flow. Our experiments show that this decomposition leads to significant improvements in three image‐based applications: denoising, spatial upsampling, and temporal interpolation.     

Replica Exchange Light Transport

We solve the light transport problem by introducing a novel unbiased Monte Carlo algorithm called replica exchange light transport, inspired by the replica exchange Monte Carlo method in the fields of computational physics and statistical information processing. The replica exchange Monte Carlo method is a sampling technique whose operation resembles simulated annealing in optimization algorithms using a set of sampling distributions. We apply it to the solution of light transport integration by extending the probability density function of an integrand of the integration to a set of distributions. That set of distributions is composed of combinations of the path densities of different path generation types: uniform distributions in the integral domain, explicit and implicit paths in light (particle/photon) tracing, indirect paths in bidirectional path tracing, explicit and implicit paths in path tracing, and implicit caustics paths seen through specular surfaces including the delta function in path tracing. The replica‐exchange light transport algorithm generates a sequence of path samples from each distribution and samples the simultaneous distribution of those distributions as a stationary distribution by using the Markov chain Monte Carlo method. Then the algorithm combines the obtained path samples from each distribution using multiple importance sampling. We compare the images generated with our algorithm to those generated with bidirectional path tracing and Metropolis light transport based on the primary sample space. Our proposing algorithm has better convergence property than bidirectional path tracing and the Metropolis light transport, and it is easy to implement by extending the Metropolis light transport.     

Shading with Curve Light Sources1

A new shading model for curve light sources is presented. It accounts for both diffuse reflection and specular reflection of the illuminated surface. By regarding a linear light source as a directional quadrilateral light source with very small width, a simple formula is derived first for calculating the diffuse reflection component due to the illumination of the linear segment. The diffuse reflection of the surface by direct illumination of a curve light source is then evaluated by approximating the curve light with a series of linear segments. The specular reflection component due to a curve light source is represented by an integration taking Phong's specular model as the kernel and evaluated by summing the contributions from the linear segments. Finally, an efficient shadow detection algorithm for curve light sources is proposed. The images rendered with the shading model are very photo-realistic.     

Fast High‐Dimensional Filtering Using the Permutohedral Lattice

Many useful algorithms for processing images and geometry fall under the general framework of high‐dimensional Gaussian filtering. This family of algorithms includes bilateral filtering and non‐local means. We propose a new way to perform such filters using the permutohedral lattice, which tessellates high‐dimensional space with uniform simplices. Our algorithm is the first implementation of a high‐dimensional Gaussian filter that is both linear in input size and polynomial in dimensionality. Furthermore it is parameter‐free, apart from the filter size, and achieves a consistently high accuracy relative to ground truth (> 45 dB). We use this to demonstrate a number of interactive‐rate applications of filters in as high as eight dimensions.     

Semantic segmentation of high-resolution images

Image semantic segmentation is a research topic that has emerged recently. Although existing approaches have achieved satisfactory accuracy, they are limited to handling low-resolution images owing to their large memory consumption. In this paper, we present a semantic segmentation method for high-resolution images. First, we downsample the input image to a lower resolution and then obtain a low-resolution semantic segmentation image using state-of-the-art methods. Next, we use joint bilateral upsampling to upsample the low-resolution solution and obtain a high-resolution semantic segmentation image. To modify joint bilateral upsampling to handle discrete semantic segmentation data, we propose using voting instead of interpolation in filtering computation. Compared to state-of-the-art methods, our method significantly reduces memory cost without reducing result quality.     

基于文档信息空间模型的词元权重调整

在web文档信息检索中,文档分类、文档过滤的质量一直是影响用户查询结果的关键。这篇论文将通过分析一些典型的权重函数的构造,提出一个基于文档信息空间的权重函数来计算调整文档中词元的权重,使文档的分类和过滤效率更高。     

基于卡方分布的高维数据相似性连接查询算法

为了解决高维数据相似性连接查询中存在的维度灾难和计算代价高等问题,基于p-稳态分布,将高维数据映射到低维空间。根据卡方分布的性质,证明了如果低维空间的距离大于kε,则原始空间距离大于ε的概率具有一定的下界,从而可以在低维空间以较低的计算代价进行有效过滤。在此基础上,提出了基于卡方分布的高维数据相似性连接查询算法。为了进一步提高查询效率,提出了基于双重过滤的高维数据相似性连接查询算法。利用真实数据集进行了实验,实验结果表明所提方法具有较好的性能。基于卡方分布的相似性连接查询算法召回率可以达到90%以上。基于双重过滤的相似性连接查询算法可以进一步提高性能,但是会损失一定的召回率。对时间性能要求比较高、对召回率要求不太严格的查询任务可以采用基于双重过滤的相似性连接查询算法;反之,可以采用基于卡方分布的相似性连接查询算法。     

Distributed entropy filtering subject to DoS attacks in non‐Gauss environments

This paper is concerned with distributed entropy filtering for a class of time‐varying systems subject to non‐Gaussian noises and denial‐of‐service attacks. A distributed Kalman‐type filter is constructed by fusing the information from neighboring sensors in the one‐step prediction estimation. The maximum correlation entropy criterion with weighted Gaussian kernels instead of the traditional least squares and minimum variance indices is then employed to evaluate the filtering performance under the more general case of non‐Gaussian noises. For the considered scenario, a new algorithm of distributed maximum correntropy criterion Kalman filters is developed by utilizing traditional fixed‐point iterative rules, and the desired filter gains are dependent on both the one‐step prediction cross‐variance and the weighted Gaussian kernel function. In light of a similar analysis process and an introduced auxiliary cost, its suboptimal version is proposed to avoid the calculation of cross‐variance and thereby satisfying the requirement of real time. Furthermore, a degenerated result is also derived under the traditional correntropy criterion (ie, with unit weighted matrices). Finally, the simulation results show the merit of proposed distributed maximum correntropy criterion Kalman filters in the presence of denial‐of‐service attacks and non‐Gaussian noises.     

Accelerating Refractive Rendering of Transparent Objects

In this paper, a technique is proposed for the rendering of transparent objects interactively using the method of refractive rendering. In the proposed technique, the refractive rendering algorithm is performed in two stages, namely the pre‐computation stage and the shading stage. In the pre‐computation stage, ray‐traced information, including directions and positions of rays, are generated by a ray tracing process and are stored in a set of ray lists. In the shading stage, these data are retrieved from the ray lists for computing the shading of an object. Using the proposed technique, photorealistic image of transparent objects and gemstones with various cuttings, material properties, lighting and background can be rendered interactively. By combining the refractive rendering technique with conventional shading techniques, jewelry and crystal designs can be rendered at a much higher speed comparing with conventional ray tracing techniques.