In this paper we develop a novel parallel spectral partitioning method that takes advantage of an efficient implementation of a preconditioned eigenvalue solver and a k-means algorithm on the GPU. We showcase the performance of our novel scheme against standard spectral techniques. Also, we use it to compare the ratio and normalized cut cost functions often used to measure the quality of graph partitioning.

Finding meaningful, structured representations of 3D point cloud data (PCD) has become a core task for spatial perception applications. In this paper we introduce a method for constructing compact generative representations of PCD at multiple levels of detail. As opposed to deterministic structures such as voxel grids or octrees, we propose probabilistic subdivisions of the data through local mixture modeling, and show how these subdivisions can provide a maximum likelihood segmentation of the data.

Automatic detection and classification of dynamic hand gestures in real-world systems intended for human computer interaction is challenging as: 1) there is a large diversity in how people perform gestures, making detection and classification difficult; 2) the system must work online in order to avoid noticeable lag between performing a gesture and its classification; in fact, a negative lag (classification even before the gesture is finished) is desirable, as the feedback to the user can then be truly instantaneous.

We present a stable shading method and a procedural shading model that enables real-time rendering of sub-pixel glints and anisotropic microdetails resulting from irregular microscopic surface structure to simulate a rich spectrum of appearances ranging from sparkling to brushed materials. We introduce a biscale Normal Distribution Function (NDF) for microdetails to provide a convenient artistic control over both the global appearance as well as over the appearance of the individual microdetail shapes, while efficiently generating procedural details.

The solution of large sparse linear systems arises in many applications, such as computational fluid dynamics and oil reservoir simulation. In realistic cases the matrices are often so large that they require large scale distributed parallel computing to obtain the solution of interest in a reasonable time. In this paper we discuss the design and implementation of the AmgX library, which provides drop-in GPU acceleration of distributed algebraic multigrid and preconditioned iterative methods.

Registration of Point Cloud Data (PCD) forms a core component of many 3D vision algorithms such as object matching and environment reconstruction. In this paper, we
introduce a PCD registration algorithm that utilizes Gaussian Mixture Models (GMM) and a novel dual-mode parameter optimization technique which we call mixture decoupling.

We introduce a method for accurate three dimensional head pose estimation using a commodity depth camera. We perform pose estimation by registering a morphable face model to the measured depth data, using a combination of particle swarm optimization (PSO) and the iterative closest point (ICP) algorithm, which minimizes a cost function that includes a 3D registration and a 2D overlap term. The pose is estimated on the fly without requiring an explicit initialization or training phase.

Accumulative anti-aliasing (ACAA) is a simple modification of forward-rendered multi-sample anti-aliasing (MSAA). It produces the same image quality but consumes half as much multi-sample framebuffer memory, and reduces both render time and off-chip bandwidth by 20% to 30%. ACAA stores multiple depth samples, computed by a depth-only pre-pass, but stores only one color sample per pixel, which is used to accumulate final color as the sum of shaded fragment colors weighted by visibility. ACAA makes higher sample rates practical, improving image quality.

As deep nets are increasingly used in applications suited for mobile devices, a fundamental dilemma becomes apparent: the trend in deep learning is to grow models to absorb ever-increasing data set sizes; however mobile devices are designed with very little memory and cannot store such large models. We present a novel network architecture, HashedNets, that exploits inherent redundancy in neural networks to achieve drastic reductions in model sizes.

The human visual system can operate in a wide range of illumination levels, due to several adaptation processes working in concert. For the most part, these adaptation mechanisms are transparent, leaving the observer unaware of his or her absolute adaptation state. At extreme illumination levels, however, some of these mechanisms produce perceivable secondary effects, or epiphenomena. In bright light, these include bleaching afterimages and adaptation afterimages, while in dark conditions these include desaturation, loss of acuity, mesopic hue shift, and the Purkinje effect.