SVBRDF Recovery from a Single Image with Highlights Using a Pre‐trained Generative Adversarial Network

Simple item page
dc.contributor.authorWen, Taoen_US
dc.contributor.authorWang, Beibeien_US
dc.contributor.authorZhang, Leien_US
dc.contributor.authorGuo, Jieen_US
dc.contributor.authorHolzschuch, Nicolasen_US
dc.contributor.editorHauser, Helwig and Alliez, Pierreen_US
dc.date.accessioned2022-10-11T05:24:55Z
dc.date.available2022-10-11T05:24:55Z
dc.date.issued2022
dc.description.abstractSpatially varying bi‐directional reflectance distribution functions (SVBRDFs) are crucial for designers to incorporate new materials in virtual scenes, making them look more realistic. Reconstruction of SVBRDFs is a long‐standing problem. Existing methods either rely on an extensive acquisition system or require huge datasets, which are non‐trivial to acquire. We aim to recover SVBRDFs from a single image, without any datasets. A single image contains incomplete information about the SVBRDF, making the reconstruction task highly ill‐posed. It is also difficult to separate between the changes in colour that are caused by the material and those caused by the illumination, without the prior knowledge learned from the dataset. In this paper, we use an unsupervised generative adversarial neural network (GAN) to recover SVBRDFs maps with a single image as input. To better separate the effects due to illumination from the effects due to the material, we add the hypothesis that the material is stationary and introduce a new loss function based on Fourier coefficients to enforce this stationarity. For efficiency, we train the network in two stages: reusing a trained model to initialize the SVBRDFs and fine‐tune it based on the input image. Our method generates high‐quality SVBRDFs maps from a single input photograph, and provides more vivid rendering results compared to the previous work. The two‐stage training boosts runtime performance, making it eight times faster than the previous work.en_US
dc.description.number6
dc.description.sectionheadersArticles
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume41
dc.identifier.doi10.1111/cgf.14514
dc.identifier.issn1467-8659
dc.identifier.pages110-123
dc.identifier.urihttps://doi.org/10.1111/cgf.14514
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14514
dc.publisher© 2022 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.en_US
dc.subjectreflectance modelling
dc.subjectSVBRDF
dc.titleSVBRDF Recovery from a Single Image with Highlights Using a Pre‐trained Generative Adversarial Networken_US
Files
Collections
41-Issue 6