2023 · 17 citations · 7 references
ArchitectureMaterials ScienceComputer VisionDigital RenderingRendering3D RenderingImage SynthesisImage-based RenderingMaterial RenderingMaterial RepresentationRendering PipelineCompressionHistogram AnalysisImportance SamplingMaterial Appearance EvaluationMaterial Appearance ModelingNeural Material RepresentationNeural RenderingRealistic Scenery
Neural material representations have recently been proposed to augment the material appearance toolbox used in realistic rendering. These models are successful at tasks ranging from measured BTF compression, through efficient rendering of synthetic displaced materials with occlusions, to BSDF layering. However, importance sampling has been an after-thought in most neural material approaches, and has been handled by inefficient cosine-hemisphere sampling or mixing it with an additional simple analytic lobe. In this paper we fill that gap, by evaluating and comparing various pdf-learning approaches for sampling spatially varying neural materials, and proposing new variations of these approaches. We investigate three sampling approaches: analytic-lobe mixtures, normalizing flows, and histogram prediction. Within each type, we introduce improvements beyond previous work, and we extensively evaluate and compare these approaches in terms of sampling rate, wall-clock time, and final visual quality. Our versions of normalizing flows and histogram mixtures perform well and can be used in practical rendering systems, potentially facilitating the broader adoption of neural material models in production.
7
Wenzel Jakob, Sébastien Speierer, Nicolas Roussel et al. · ACM Transactions on Graphics · 2022 · 127 citations · Full text
Alexandr Kuznetsov, Krishna Mullia, Zexiang Xu et al. · ACM Transactions on Graphics · 2021 · 59 citations · Full text
Unified Neural Encoding of BTFs
Gilles Rainer, Abhijeet Ghosh, Wenzel Jakob et al. · Computer Graphics Forum · 2020 · 51 citations · Full text
Jiahui Fan, Beibei Wang, Miloš Hašan et al. · 2022 · 25 citations
Rendering Neural Materials on Curved Surfaces
Alexandr Kuznetsov, Xuezheng Wang, Krishna Mullia et al. · 2022 · 24 citations · Full text