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 . Papers surveyed in this study with a focus on the extraction of BRDF or SVBRDF from a few measurements, classifying them according to their specific geometries and lighting conditions. Whole-scene refers to techniques that capture entire indoor or outdoor outside the scope of this survey. image

Deep learning advancements have significantly enhanced computer vision applications in precision agriculture. While RGB cameras operating in visible light are affordable, they provide limited information compared to multispectral equipment. This research analyses methods to reduce the need for manual annotation when training a model using only RGB images, without compromising the model's accuracy. We propose a semi-supervised approach where a teacher model, trained on multispectral images, generates artificial ground truth data to train a student model that operates solely on RGB images. This strategy has enabled us to achieve nearly a tenfold reduction in the required training data while maintaining similar performance metrics. Additionally, we explore the potential of segmentation foundation models to simplify the manual annotation process, reducing the need for full segmentation masks to just bounding boxes. Our findings also indicate that using multispectral images as input for the Segment Anything Model is more effective than using RGB images.

In this paper, we propose a novel GPU-based method for highly parallel compressed sensing of n-dimensional (nD) signals based on the smoothed l(0) (SL0) algorithm. We demonstrate the efficiency of our approach by showing several examples of nD tensor reconstructions. Moreover, we also consider the traditional 1D compressed sensing, and compare the results. We show that the multidimensional SL0 algorithm is computationally superior compared to the 1D variant due to the small dictionary sizes per dimension. This allows us to fully utilize the GPU and perform massive batch-wise computations, which is not possible for the 1D compressed sensing using SL0. For our evaluations, we use light field and light field video data sets. We show that we gain more than an order of magnitude speedup for both one-dimensional as well as multidimensional data points compared to a parallel CPU implementation. Finally, we present a theoretical analysis of the SL0 algorithm for nD signals, which generalizes previous work for 1D signals.

Photorealistic rendering is an essential tool for immersive virtual reality. In this regard, the data structure of choice is typically light fields since they contain multidimensional information about the captured environment that can provide motion parallax and view-dependent information such as highlights. There are various ways to acquire light fields depending on the nature of the scene, limitations on the capturing setup, and the application at hand. Our focus in this paper is on full-parallax imaging of large-scale static objects for photorealistic real-time rendering. To this end, we introduce and simulate a new design for capturing inward-looking spherical light fields, and propose a system for efficient compression and real-time rendering of such data using consumer-level hardware suitable for virtual reality applications.

We present a method for GPU accelerated compression of light fields. The approach is by using a dictionary learning framework for compression of light field images. The large amount of data storage by capturing light fields is a challenge to compress and we seek to accelerate the encoding routine by GPGPU computations. We compress the data by projecting each data point onto a set of trained multi-dimensional dictionaries and seek the most sparse representation with the least error. This is done by a parallelization of the tensor-matrix product computed on the GPU. An optimized greedy algorithm to suit computations on the GPU is also presented. The encoding of the data is done segmentally in parallel for a faster computation speed while maintaining the quality. The results shows an order of magnitude faster encoding time compared to the results in the same research field. We conclude that there are further improvements to increase the speed, and thus it is not too far from an interacti ve compression speed.