Abstract Material appearance is commonly modeled with the Bidirectional Reflectance Distribution Functions (BRDFs), which need to trade accuracy for complexity and storage cost. To investigate the current practices of BRDF modeling, we collect the first high dynamic range stereoscopic video dataset that captures the perceived quality degradation with respect to a number of parametric and non‐parametric BRDF models. Our dataset shows that the current loss functions used to fit BRDF models, such as mean‐squared error of logarithmic reflectance values, correlate poorly with the perceived quality of materials in rendered videos. We further show that quality metrics that compare rendered material samples give a significantly higher correlation with subjective quality judgments, and a simple Euclidean distance in the ITP color space (ΔEITP) shows the highest correlation. Additionally, we investigate the use of different BRDF‐space metrics as loss functions for fitting BRDF models and find that logarithmic mapping is the most effective approach for BRDF‐space loss functions.

Abstract Hand in hand with the rapid development of machine learning, deep learning and generative AI algorithms and architectures, the graphics community has seen a remarkable evolution of novel techniques for material and appearance capture. Typically, these machine‐learning‐driven methods and technologies, in contrast to traditional techniques, rely on only a single or very few input images, while enabling the recovery of detailed, high‐quality measurements of bi‐directional reflectance distribution functions, as well as the corresponding spatially varying material properties, also known as Spatially Varying Bi‐directional Reflectance Distribution Functions (SVBRDFs). Learning‐based approaches for appearance capture will play a key role in the development of new technologies that will exhibit a significant impact on virtually all domains of graphics. Therefore, to facilitate future research, this State‐of‐the‐Art Report (STAR) presents an in‐depth overview of the state‐of‐the‐art in machine‐learning‐driven material capture in general, and focuses on SVBRDF acquisition in particular, due to its importance in accurately modelling complex light interaction properties of real‐world materials. The overview includes a categorization of current methods along with a summary of each technique, an evaluation of their functionalities, their complexity in terms of acquisition requirements, computational aspects and usability constraints. The STAR is concluded by looking forward and summarizing open challenges in research and development toward predictive and general appearance capture in this field. A complete list of the methods and papers reviewed in this survey is available at computergraphics.on.liu.se/star_svbrdf_dl/ .

Abstract Diffusion‐weighted magnetic resonance imaging (D‐MRI) is a technique to measure the diffusion of water, in biological tissues. It is used to detect microscopic patterns, such as neural fibers in the living human brain, with many medical and neuroscience applications e.g. for fiber tracking. In this paper, we consider High‐Angular Resolution Diffusion Imaging (HARDI) which provides one of the richest representations of water diffusion. It records the movement of water molecules by measuring diffusion under 64 or more directions. A key challenge is that it generates high‐dimensional, large, and complex datasets. In our work, we develop a novel representation that exploits the inherent sparsity of the HARDI signal by approximating it as a linear sum of basic atoms in an overcomplete data‐driven dictionary using only a sparse set of coefficients. We show that this approach can be efficiently integrated into the standard q‐ball imaging pipeline to compute the diffusion orientation distribution function (ODF). Sparse representations have the potential to reduce the size of the data while also giving some insight into the data. To explore the results, we provide a visualization of the atoms of the dictionary and their frequency in the data to highlight the basic characteristics of the data. We present our proposed pipeline and demonstrate its performance on 5 HARDI datasets.

Efficient and accurate BRDF acquisition of real world materials is a challenging research problem that requires sampling millions of incident light and viewing directions. To accelerate the acquisition process, one needs to find a minimal set of sampling directions such that the recovery of the full BRDF is accurate and robust given such samples. In this article, we formulate BRDF acquisition as a compressed sensing problem, where the sensing operator is one that performs sub-sampling of the BRDF signal according to a set of optimal sample directions. To solve this problem, we propose the Fast and Robust Optimal Sampling Technique (FROST) for designing a provably optimal sub-sampling operator that places light-view samples such that the recovery error is minimized. FROST casts the problem of designing an optimal sub-sampling operator for compressed sensing into a sparse representation formulation under the Multiple Measurement Vector (MMV) signal model. The proposed reformulation is exact, i.e. without any approximations, hence it converts an intractable combinatorial problem into one that can be solved with standard optimization techniques. As a result, FROST is accompanied by strong theoretical guarantees from the field of compressed sensing. We perform a thorough analysis of FROST-BRDF using a 10-fold cross-validation with publicly available BRDF datasets and show significant advantages compared to the state-of-the-art with respect to reconstruction quality. Finally, FROST is simple, both conceptually and in terms of implementation, it produces consistent results at each run, and it is at least two orders of magnitude faster than the prior art.

We propose a novel dictionary-based representation learning model for Bidirectional Texture Functions (BTFs) aiming at compact storage, real-time rendering performance, and high image quality. Our model is trained once, using a small training set, and then used to obtain a sparse tensor containing the model parameters. Our technique exploits redundancies in the data across all dimensions simultaneously, as opposed to existing methods that use only angular information and ignore correlations in the spatial domain. We show that our model admits efficient angular interpolation directly in the model space, rather than the BTF space, leading to a notably higher rendering speed than in previous work. Additionally, the high quality-storage cost tradeoff enabled by our method facilitates controlling the image quality, storage cost, and rendering speed using a single parameter, the number of coefficients. Previous methods rely on a fixed number of latent variables for training and testing, hence limiting the potential for achieving a favorable quality-storage cost tradeoff and scalability. Our experimental results demonstrate that our method outperforms existing methods both quantitatively and qualitatively, as well as achieving a higher compression ratio and rendering speed.

In this paper, we introduce a novel 6-D representation of plenoptic point clouds, enabling joint, non-separable transform coding of plenoptic signals defined along both spatial and angular (viewpoint) dimensions. This 6-D representation, which is built in a global coordinate system, can be used in both multi-camera studio capture and video fly-by capture scenarios, with various viewpoint (camera) arrangements and densities. We show that both the Region-Adaptive Hierarchical Transform (RAHT) and the Graph Fourier Transform (GFT) can be extended to the proposed 6-D representation to enable the non-separable transform coding. Our method is applicable to plenoptic data with either dense or sparse sets of viewpoints, and tocompleteorincompleteplenoptic data, while the state-of-the-art RAHT-KLT method, which is separable in spatial and angular dimensions, is applicable only tocompleteplenoptic data. The “complete” plenoptic data refers to data that has, for each spatial point, one colour for every viewpoint (ignoring any occlusions), while “incomplete” data has colours only for thevisiblesurface points at each viewpoint. We demonstrate that the proposed 6-D RAHT and 6-D GFT compression methods are able to outperform the state-of-the-art RAHT-KLT method on 3-D objects with various levels of surface specularity, and captured with different camera arrangements and different degrees of viewpoint sparsity.

This paper presents a novel sparse non-parametric Bidirectional Reflectance Distribution Function (BRDF) model derived using a machine learning approach to represent the space of possible BRDFs using a set of multidimensional sub-spaces, or dictionaries. By training the dictionaries under a sparsity constraint, the model guarantees high-quality representations with minimal storage requirements and an inherent clustering of the BDRF-space. The model can be trained once and then reused to represent a wide variety of measured BRDFs. Moreover, the proposed method is flexible to incorporate new unobserved data sets, parameterizations, and transformations. In addition, we show that any two, or more, BRDFs can be smoothly interpolated in the coefficient space of the model rather than the significantly higher-dimensional BRDF space. The proposed sparse BRDF model is evaluated using the MERL, DTU, and RGL-EPFL BRDF databases. Experimental results show that the proposed approach results in about 9.75dB higher signal-to-noise ratio on average for rendered images as compared to current state-of-the-art models.

Abstract This paper presents a novel compressed sensing (CS) algorithm and camera design for light field video capture using a single sensor consumer camera module. Unlike microlens light field cameras which sacrifice spatial resolution to obtain angular information, our CS approach is designed for capturing light field videos with high angular, spatial, and temporal resolution. The compressive measurements required by CS are obtained using a random color‐coded mask placed between the sensor and aperture planes. The convolution of the incoming light rays from different angles with the mask results in a single image on the sensor; hence, achieving a significant reduction on the required bandwidth for capturing light field videos. We propose to change the random pattern on the spectral mask between each consecutive frame in a video sequence and extracting spatio‐angular‐spectral‐temporal 6D patches. Our CS reconstruction algorithm for light field videos recovers each frame while taking into account the neighboring frames to achieve significantly higher reconstruction quality with reduced temporal incoherencies, as compared with previous methods. Moreover, a thorough analysis of various sensing models for compressive light field video acquisition is conducted to highlight the advantages of our method. The results show a clear advantage of our method for monochrome sensors, as well as sensors with color filter arrays.

Abstract Light field imaging is rapidly becoming an established method for generating flexible image based description of scene appearances. Compared to classical 2D imaging techniques, the angular information included in light fields enables effects such as post‐capture refocusing and the exploration of the scene from different vantage points. In this paper, we describe a novel GPU pipeline for compression and real‐time rendering of light field videos with full parallax. To achieve this, we employ a dictionary learning approach and train an ensemble of dictionaries capable of efficiently representing light field video data using highly sparse coefficient sets. A novel, key element in our representation is that we simultaneously compress both image data (pixel colors) and the auxiliary information (depth, disparity, or optical flow) required for view interpolation. During playback, the coefficients are streamed to the GPU where the light field and the auxiliary information are reconstructed using the dictionary ensemble and view interpolation is performed. In order to realize the pipeline we present several technical contributions including a denoising scheme enhancing the sparsity in the dataset which enables higher compression ratios, and a novel pruning strategy which reduces the size of the dictionary ensemble and leads to significant reductions in computational complexity during the encoding of a light field. Our approach is independent of the light field parameterization and can be used with data from any light field video capture system. To demonstrate the usefulness of our pipeline, we utilize various publicly available light field video datasets and discuss the medical application of documenting heart surgery.

In this article we present a novel dictionary learning framework designed for compression and sampling of light fields and light field videos. Unlike previous methods, where a single dictionary with one-dimensional atoms is learned, we propose to train a Multidimensional Dictionary Ensemble (MDE). It is shown that learning an ensemble in the native dimensionality of the data promotes sparsity, hence increasing the compression ratio and sampling efficiency. To make maximum use of correlations within the light field data sets, we also introduce a novel nonlocal pre-clustering approach that constructs an Aggregate MDE (AMDE). The pre-clustering not only improves the image quality but also reduces the training time by an order of magnitude in most cases. The decoding algorithm supports efficient local reconstruction of the compressed data, which enables efficient real-time playback of high-resolution light field videos. Moreover, we discuss the application of AMDE for compressed sensing. A theoretical analysis is presented that indicates the required conditions for exact recovery of point-sampled light fields that are sparse under AMDE. The analysis provides guidelines for designing efficient compressive light field cameras. We use various synthetic and natural light field and light field video data sets to demonstrate the utility of our approach in comparison with the state-of-the-art learning-based dictionaries, as well as established analytical dictionaries.

In this letter, we present a new coherence-based performance guarantee for the orthogonal matching pursuit (OMP) algorithm. A lower bound for the probability of correctly identifying the support of a sparse signal with additive white Gaussian noise is derived. Compared to previous research work, the new bound takes into account the signal parameters, such as dynamic range, noise variance, and sparsity. Numerical simulations show significant improvements over previous research work and a closer match to empirically obtained results of the OMP algorithm.

In this paper we consider the problem of nonlocal image completion from random measurements and using an ensemble of dictionaries. Utilizing recent advances in the field of compressed sensing, we derive conditions under which one can uniquely recover an incomplete image with overwhelming probability. The theoretical results are complemented by numerical simulations using various ensembles of analytical and training-based dictionaries.

Abstract Photo‐realistic rendering of virtual objects into real scenes is one of the most important research problems in computer graphics. Methods for capture and rendering of mixed reality scenes are driven by a large number of applications, ranging from augmented reality to visual effects and product visualization. Recent developments in computer graphics, computer vision, and imaging technology have enabled a wide range of new mixed reality techniques including methods for advanced image based lighting, capturing spatially varying lighting conditions, and algorithms for seamlessly rendering virtual objects directly into photographs without explicit measurements of the scene lighting. This report gives an overview of the state‐of‐the‐art in this field, and presents a categorization and comparison of current methods. Our in‐depth survey provides a tool for understanding the advantages and disadvantages of each method, and gives an overview of which technique is best suited to a specific problem.

Abstract We present a new compressed sensing framework for reconstruction of incomplete and possibly noisy images and their higher dimensional variants, e.g. animations and light‐fields. The algorithm relies on a learning‐based basis representation. We train an ensemble of intrinsically two‐dimensional (2D) dictionaries that operate locally on a set of 2D patches extracted from the input data. We show that one can convert the problem of 2D sparse signal recovery to an equivalent 1D form, enabling us to utilize a large family of sparse solvers. The proposed framework represents the input signals in a reduced union of subspaces model, while allowing sparsity in each subspace. Such a model leads to a much more sparse representation than widely used methods such as K‐SVD. To evaluate our method, we apply it to three different scenarios where the signal dimensionality varies from 2D (images) to 3D (animations) and 4D (light‐fields). We show that our method outperforms state‐of‐the‐art algorithms in computer graphics and image processing literature.