Show simple item record

dc.contributor.authorLuo, Xuejiaoen_US
dc.contributor.authorScandolo, Leonardoen_US
dc.contributor.authorBousseau, Adrienen_US
dc.contributor.authorEisemann, Elmaren_US
dc.contributor.editorBermano, Amit H.en_US
dc.contributor.editorKalogerakis, Evangelosen_US
dc.date.accessioned2024-04-16T14:38:46Z
dc.date.available2024-04-16T14:38:46Z
dc.date.issued2024
dc.identifier.issn1467-8659
dc.identifier.urihttps://doi.org/10.1111/cgf.15018
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf15018
dc.description.abstractRecovering spatially-varying materials from a single photograph of a surface is inherently ill-posed, making the direct application of a gradient descent on the reflectance parameters prone to poor minima. Recent methods leverage deep learning either by directly regressing reflectance parameters using feed-forward neural networks or by learning a latent space of SVBRDFs using encoder-decoder or generative adversarial networks followed by a gradient-based optimization in latent space. The former is fast but does not account for the likelihood of the prediction, i.e., how well the resulting reflectance explains the input image. The latter provides a strong prior on the space of spatially-varying materials, but this prior can hinder the reconstruction of images that are too different from the training data. Our method combines the strengths of both approaches. We optimize reflectance parameters to best reconstruct the input image using a recurrent neural network, which iteratively predicts how to update the reflectance parameters given the gradient of the reconstruction likelihood. By combining a learned prior with a likelihood measure, our approach provides a maximum a posteriori estimate of the SVBRDF. Our evaluation shows that this learned gradient-descent method achieves state-of-the-art performance for SVBRDF estimation on synthetic and real images.en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Rendering -> Reflectance/Shading Models
dc.subjectRendering
dc.subjectReflectance/Shading Models
dc.titleSingle-Image SVBRDF Estimation with Learned Gradient Descenten_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersReflectance and Shading Models
dc.description.volume43
dc.description.number2
dc.identifier.doi10.1111/cgf.15018
dc.identifier.pages12 pages


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record