Understanding how people explore immersive virtual environments is crucial for many applications, such as designing virtual reality (VR) content, developing new compression algorithms, or learning computational models of saliency or visual attention. Whereas a body of recent work has focused on modeling saliency in desktop viewing conditions, VR is very different from these conditions in that viewing behavior is governed by stereoscopic vision and by the complex interaction of head orientation, gaze, and other kinematic constraints. To further our understanding of viewing behavior and saliency in VR, we capture and analyze gaze and head orientation data of 169 users exploring stereoscopic, static omni-directional panoramas, for a total of 1980 head and gaze trajectories for three different viewing conditions. We provide a thorough analysis of our data, which leads to several important insights, such as the existence of a particular fixation bias, which we then use to adapt existing saliency predictors to immersive VR conditions. In addition, we explore other applications of our data and analysis, including automatic alignment of VR video cuts, panorama thumbnails, panorama video synopsis, and saliency-basedcompression.

This supplemental document contains the following information:A Overview of the method B Derivation of the phasor field C LOS template functions D Implementation details of the RSD solvers

Recent advances in ultra-fast imaging have triggered many promising applications in graphics and vision, such as capturing transparent objects, estimating hidden geometry and materials, or visualizing light in motion. There is, however, very little work regarding the effective simulation and analysis of transient light transport, where the speed of light can no longer be considered infinite. We first introduce the transient path integral framework, formally describing light transport in transient state. We then analyze the difficulties arising when considering the light's time-of-flight in the simulation (rendering) of images and videos. We propose a novel density estimation technique that allows reusing sampled paths to reconstruct time-resolved radiance, and devise new sampling strategies that take into account the distribution of radiance along time in participating media. We then efficiently simulate time-resolved phenomena (such as caustic propagation, fluorescence or temporal chromatic dispersion), which can help design future ultra-fast imaging devices using an analysis-by-synthesis approach, as well as to achieve a better understanding of the nature of light transport.

We present a novel hyperspectral image reconstruction algorithm, which overcomes the long-standing tradeoff between spectral accuracy and spatial resolution in existing compressive imaging approaches. Our method consists of two steps: First, we learn nonlinear spectral representations from real-world hyperspectral datasets; for this, we build a convolutional autoencoder which allows reconstructing its own input through its encoder and decoder networks. Second, we introduce a novel optimization method, which jointly regularizes the fidelity of the learned nonlinear spectral representations and the sparsity of gradients in the spatial domain, by means of our new fidelity prior. Our technique can be applied to any existing compressive imaging architecture, and has been thoroughly tested both in simulation, and by building a prototype hyperspectral imaging system. It outperforms the state-of-the-art methods from each architecture, both in terms of spectral accuracy and spatial resolution, while its computational complexity is reduced by two orders of magnitude with respect to sparse coding techniques. Moreover, we present two additional applications of our method: hyperspectral interpolation and demosaicing. Last, we have created a new high-resolution hyperspectral dataset containing sharper images of more spectral variety than existing ones, available through our project website.

Capturing spatially-varying bidirectional reflectance distribution functions (SVBRDFs) of 3D objects with just a single, hand-held camera (such as an off-the-shelf smartphone or a DSLR camera) is a difficult, open problem. Previous works are either limited to planar geometry, or rely on previously scanned 3D geometry, thus limiting their practicality. There are several technical challenges that need to be overcome: First, the built-in flash of a camera is almost colocated with the lens, and at a fixed position; this severely hampers sampling procedures in the light-view space. Moreover, the near-field flash lights the object partially and unevenly. In terms of geometry, existing multiview stereo techniques assume diffuse reflectance only, which leads to overly smoothed 3D reconstructions, as we show in this paper. We present a simple yet powerful framework that removes the need for expensive, dedicated hardware, enabling practical acquisition of SVBRDF information from real-world, 3D objects with a single, off-the-shelf camera with a built-in flash. In addition, by removing the diffuse reflection assumption and leveraging instead such SVBRDF information, our method outputs high-quality 3D geometry reconstructions, including more accurate high-frequency details than state-of-the-art multiview stereo techniques. We formulate the joint reconstruction of SVBRDFs, shading normals, and 3D geometry as a multi-stage, iterative inverse-rendering reconstruction pipeline. Our method is also directly applicable to any existing multiview 3D reconstruction technique. We present results of captured objects with complex geometry and reflectance; we also validate our method numerically against other existing approaches that rely on dedicated hardware, additional sources of information, or both.

CRSV MULTIOP SC SCL SM SNS WARP Figure 1: Example of retargeting the butterfly image shown in Figure 2 to half its size. In this study we evaluate 8 different image retargeting methods, asking users to compare their results and examine what qualities in retargeted images mattered to them. We also correlate the users' preferences with automatic image similarity measures. Our findings provide insights on the retargeting problem, and present a clear benchmark for future research in the field. AbstractThe numerous works on media retargeting call for a methodological approach for evaluating retargeting results. We present the first comprehensive perceptual study and analysis of image retargeting. First, we create a benchmark of images and conduct a large scale user study to compare a representative number of state-of-the-art retargeting methods. Second, we present analysis of the users' responses, where we find that humans in general agree on the evaluation of the results and show that some retargeting methods are consistently more favorable than others. Third, we examine whether computational image distance metrics can predict human retargeting perception. We show that current measures used in this context are not necessarily consistent with human rankings, and demonstrate that better results can be achieved using image features that were not previously considered for this task. We also reveal specific qualities in retargeted media that are more important for viewers. The importance of our work lies in promoting better measures to assess and guide retargeting algorithms in the future. The full benchmark we collected, including all images, retargeted results, and the collected user data, are available to the research community for further investigation at

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.

Figure 1: Using our control space to achieve fast, intuitive edits of material appearance. We increasingly modify the metallic appearance of a fabric-like BRDF from the MERL database (red-fabric2), yielding intuitive changes in appearance by simply adjusting one of our perceptual attributes. Key to this ease of use and predictability of the results is our novel functionals, which map the coefficients of the first five principal components (PC) of the BRDF representation to the expected behavior of the perceptual attributes, based on a large-scale user study comprising 56,000 ratings. The rightmost plot shows the path followed by this edit in our control space. Other applications of our novel space include appearance similarity metrics, mapping perceptual attributes to analytic BRDFs, or guidance for gamut mapping. AbstractMany different techniques for measuring material appearance have been proposed in the last few years. These have produced large public datasets, which have been used for accurate, data-driven appearance modeling. However, although these datasets have allowed us to reach an unprecedented level of realism in visual appearance, editing the captured data remains a challenge. In this paper, we present an intuitive control space for predictable editing of captured BRDF data, which allows for artistic creation of plausible novel material appearances, bypassing the difficulty of acquiring novel samples. We first synthesize novel materials, extending the existing MERL dataset up to 400 mathematically valid BRDFs. We then design a large-scale experiment, gathering 56,000 subjective ratings on the high-level perceptual attributes that best describe our extended dataset of materials. Using these ratings, we build and train networks of radial basis functions to act as functionals mapping the perceptual attributes to an underlying PCA-based representation of BRDFs. We show that our functionals are excellent predictors of the perceived attributes of appearance. Our control space enables many applications, including intuitive material editing of a wide range of visual properties, guidance for gamut mapping, analysis of the correlation between perceptual attributes, or novel appearance similarity metrics. Moreover, our methodology can be used to derive functionals applicable to classic analytic BRDF representations. We release our code and dataset publicly, in order to support and encourage further research in this direction.