Data Driven Reflectance Acquisition And Modeling For Predictive Rendering

Data-driven Reflectance Acquisition and Modeling for Predictive Rendering

Recent developments in computer graphics, and particularly within predictive rendering, have enabled highly realistic simulations of object appearances. While physically-based reflectance (PBR) models offer widespread utility, measured material reflectance data yields significantly higher accuracy through the direct empirical observation of complex light-scattering interactions. Nevertheless, acquiring and modeling reflectance data entails substantial computational overhead. This thesis investigates data-driven approaches to improve the acquisition, representation, and rendering of reflectance data, with a focus on predictive rendering to achieve precise and reliable visual simulations. The first part of the thesis focuses on acquisition of Bidirectional Reflectance Distribution Function (BRDF) and Spatially Varying BRDF (SVBRDF)—functions that describe light-surface interactions at each point based on incoming and reflected light directions. Lightweight setups are initially explored to enable efficient SVBRDF capture; however, their accuracy falls short for predictive rendering applications, motivating the adoption of gonioreflectometer-based setups. To improve measurement efficiency of such setups, a compressed sensing framework is introduced, which incorporates a deterministic sampling strategy. Additionally, a unified formulation for sparse BRDF acquisition is presented, allowing for the adaptation of sampling patterns and sample counts to the unique properties of each material. This approach significantly enhances reconstruction quality while preserving the same sampling budget. The second part of the thesis addresses modeling of reflectance measurements, particularly the Bidirectional Texture Function (BTF) and BRDF. Sparse representation techniques applied to existing BTF datasets prove effective in compressing texture data while enabling real-time rendering of the measured BTFs. Despite these advances, a discrepancy often arises between model-space errors introduced during approximation and the image-space errors perceived in rendered outputs. To bridge this gap, a systematic psychophysical experiment is performed to analyze the impact of BRDF modeling techniques on rendered material quality. Building on these findings, a neural metric is developed to evaluate perceptual accuracy directly in BRDF-space. This metric exhibits strong correlation with subjective human evaluations and presents the potential to guide BRDF fitting algorithms toward solutions that produce visually accurate and compelling renderings of real-world materials.

Data-driven Reflectance Acquisition and Modeling for Predictive Rendering

Data-Driven Approaches for Efficient Smart Grid Systems

This Research Topic aims to highlight the exciting potential of innovative forecasting methods and their practical applications using machine learning in smart grid systems (SGSs). Machine learning techniques, which encompass traditional neural networks and advanced deep learning methods, have gained significant attention for their ability to address the complex challenges within SGSs and simultaneously improve cost-effectiveness. It's important to note that when machine learning models are employed in SGSs, they primarily focus on forecasting. This emphasis is grounded in the models' impressive capability to accurately replicate the intricate dynamics that characterize smart grid systems. By harnessing these forecasting models, researchers and practitioners are equipped with a valuable tool to better understand and predict the behavior of SGSs. This not only contributes to academic advancements but also enhances the practical implementation of smart grid technologies.