Observing and recognizing materials is a fundamental part of our daily life. Under typical viewing conditions, we are capable of effortlessly identifying the objects that surround us and recognizing the materials they are made of. Nevertheless, understanding the underlying perceptual processes that take place to accurately discern the visual properties of an object is a long-standing problem. In this work, we perform a comprehensive and systematic analysis of how the interplay of geometry, illumination, and their spatial frequencies affects human performance on material recognition tasks. We carry out large-scale behavioral experiments where participants are asked to recognize different reference materials among a pool of candidate samples. In the different experiments, we carefully sample the information in the frequency domain of the stimuli. From our analysis, we find significant first-order interactions between the geometry and the illumination, of both the reference and the candidates. In addition, we observe that simple image statistics and higher-order image histograms do not correlate with human performance. Therefore, we perform a high-level comparison of highly non-linear statistics by training a deep neural network on material recognition tasks. Our results show that such models can accurately classify materials, which suggests that they are capable of defining a meaningful representation of material appearance from labeled proximal image data. Last, we find preliminary evidence that these highly non-linear models and humans may use similar high-level factors for material recognition tasks.
We present a model to measure the similarity in appearance between different materials, which correlates with human similarity judgments. We first create a database of 9,000 rendered images depicting objects with varying materials, shape and illumination. We then gather data on perceived similarity from crowdsourced experiments; our analysis of over 114,840 answers suggests that indeed a shared perception of appearance similarity exists. We feed this data to a deep learning architecture with a novel loss function, which learns a feature space for materials that correlates with such perceived appearance similarity. Our evaluation shows that our model outperforms existing metrics. Last, we demonstrate several applications enabled by our metric, including appearance-based search for material suggestions, database visualization, clustering and summarization, and gamut mapping.
Selecting an optimal set of icons is a crucial step in the pipeline of visual design to structure and navigate through content. However, designing the icons sets is usually a difficult task for which expert knowledge is required. In this work, to ease the process of icon set selection to the users, we propose a similarity metric which captures the properties of style and visual identity. We train a Siamese Neural Network with an online dataset of icons organized in visually coherent collections that are used to adaptively sample training data and optimize the training process. As the dataset contains noise, we further collect human-rated information on the perception of icon's similarity which will be used for evaluating and testing the proposed model. We present several results and applications based on searches, kernel visualizations and optimized set proposals that can be helpful for designers and non-expert users while exploring large collections of icons.
Non-Line-of-Sight (NLOS) imaging allows to observe objects partially or fully occluded from direct view, by analyzing indirect diffuse reflections off a secondary, relay surface. Despite its many potential applications, existing methods lack practical usability due to several shared limitations, including the assumption of single scattering only, lack of occlusions, and Lambertian reflectance. We lift these limitations by transforming the NLOS problem into a virtual Line-Of-Sight (LOS) one. Since imaging information cannot be recovered from the irradiance arriving at the relay surface, we introduce the concept of the phasor field, a mathematical construct representing a fast variation in irradiance. We show that NLOS light transport can be modeled as the propagation of a phasor field wave, which can be solved accurately by the Rayleigh-Sommerfeld diffraction integral. We demonstrate for the first time NLOS reconstruction of complex scenes with strong multiply scattered and ambient light, arbitrary materials, large depth range, and occlusions. Our method handles these challenging cases without explicitly developing a light transport model. By leveraging existing fast algorithms, we outperform existing methods in terms of execution speed, computational complexity, and memory use. We believe that our approach will help unlock the potential of NLOS imaging, and the development of novel applications not restricted to lab conditions. For example, we demonstrate both refocusing and transient NLOS videos of real-world, complex scenes with large depth.
Current HDR acquisition techniques are based on either (i) fusing multibracketed, low dynamic range (LDR) images, (ii) modifying existing hardware and capturing different exposures simultaneously with multiple sensors, or (iii) reconstructing a single image with spatially-varying pixel exposures. In this paper, we propose a novel algorithm to recover high-quality HDRI images from a single, coded exposure. The proposed reconstruction method builds on recently-introduced ideas of convolutional sparse coding (CSC); this paper demonstrates how to make CSC practical for HDR imaging. We demonstrate that the proposed algorithm achieves higher-quality reconstructions than alternative methods, we evaluate optical coding schemes, analyze algorithmic parameters, and build a prototype coded HDR camera that demonstrates the utility of convolutional sparse HDRI coding with a custom hardware platform.
Video capture is limited by the trade-off between spatial and temporal resolution: when capturing videos of high temporal resolution, the spatial resolution decreases due to bandwidth limitations in the capture system. Achieving both high spatial and temporal resolution is only possible with highly specialized and very expensive hardware, and even then the same basic trade-off remains. The recent introduction of compressive sensing and sparse reconstruction techniques allows for the capture of single-shot high-speed video, by coding the temporal information in a single frame, and then reconstructing the full video sequence from this single coded image and a trained dictionary of image patches. In this paper, we first analyze this approach, and find insights that help improve the quality of the reconstructed videos. We then introduce a novel technique, based on convolutional sparse coding (CSC), and show how it outperforms the state-of-the-art, patch-based approach in terms of flexibility and efficiency, due to the convolutional nature of its filter banks. The key idea for CSC high-speed video acquisition is extending the basic formulation by imposing an additional constraint in the temporal dimension, which enforces sparsity of the first-order derivatives over time.
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-based compression.
Recent works have demonstrated non-line of sight (NLOS) reconstruction by using the time-resolved signal frommultiply scattered light. These works combine ultrafast imaging systems with computation, which back-projects the recorded space-time signal to build a probabilistic map of the hidden geometry. Unfortunately, this computation is slow, becoming a bottleneck as the imaging technology improves. In this work, we propose a new back-projection technique for NLOS reconstruction, which is up to a thousand times faster than previous work, with almost no quality loss. We base on the observation that the hidden geometry probability map can be built as the intersection of the three-bounce space-time manifolds defined by the light illuminating the hidden geometry and the visible point receiving the scattered light from such hidden geometry. This allows us to pose the reconstruction of the hidden geometry as the voxelization of these space-time manifolds, which has lower theoretic complexity and is easily implementable in the GPU. We demonstrate the efficiency and quality of our technique compared against previous methods in both captured and synthetic data
We present a method to automatically decompose a light field into its intrinsic shading and albedo components. Contrary to previous work targeted to 2D single images and videos, a light field is a 4D structure that captures non-integrated incoming radiance over a discrete angular domain. This higher dimensionality of the problem renders previous state-of-the-art algorithms impractical either due to their cost of processing a single 2D slice, or their inability to enforce proper coherence in additional dimensions. We propose a new decomposition algorithm that jointly optimizes the whole light field data for proper angular coherence. For efficiency, we extend Retinex theory, working on the gradient domain, where new albedo and occlusion terms are introduced. Results show our method provides 4D intrinsic decompositions difficult to achieve with previous state-of-the-art algorithms. We further provide a comprehensive analysis and comparisons with existing intrinsic image/video decomposition methods on light field images.
Single-Photon Avalanche Diodes (SPAD) are affordable photodetectors, capable to collect extremely fast low-energy events, due to their single-photon sensibility. This makes them very suitable for time-of-flight-based range imaging systems, allowing to reduce costs and power requirements, without sacrifizing much temporal resolution. In this work we describe a computational model to simulate the behaviour of SPAD sensors, aiming to provide a realistic camera model for time-resolved light transport simulation, with applications on prototyping new reconstructions techniques based on SPAD time-of-flight data. Our model accounts for the major effects of the sensor on the incoming signal. We compare our model against real-world measurements, and apply it to a variety of scenarios, including complex multiply-scattered light transport.