Show simple item record

dc.contributor.authorKassubeck, Marcen_US
dc.contributor.authorKappel, Moritzen_US
dc.contributor.authorCastillo, Susanaen_US
dc.contributor.authorMagnor, Marcusen_US
dc.contributor.editorGuthe, Michaelen_US
dc.contributor.editorGrosch, Thorstenen_US
dc.date.accessioned2023-09-25T11:36:40Z
dc.date.available2023-09-25T11:36:40Z
dc.date.issued2023
dc.identifier.isbn978-3-03868-232-5
dc.identifier.urihttps://doi.org/10.2312/vmv.20231224
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/vmv20231224
dc.description.abstractThis paper handles the highly challenging problem of reconstructing the shape of a refracting object from a single image of its resulting caustic. Due to the ubiquity of transparent refracting objects in everyday life, reconstruction of their shape entails a multitude of practical applications. While we focus our attention on inline shape reconstruction in glass fabrication processes, our methodology could be adapted to scenarios where the limiting factor is a lack of input measurements to constrain the reconstruction problem completely. The recent Shape from Caustics (SfC) method casts this problem as the inverse of a light propagation simulation for synthesis of the caustic image, that can be solved by a differentiable renderer. However, the inherent complexity of light transport through refracting surfaces currently limits the practical application due to reconstruction speed and robustness. Thus, we introduce Neural-Shape from Caustics (N-SfC), a learning-based extension incorporating two components into the reconstruction pipeline: a denoising module, which both alleviates the light transport simulation cost, and also helps finding a better minimum; and an optimization process based on learned gradient descent, which enables better convergence using fewer iterations. Extensive experiments demonstrate that we significantly outperform the current state-of-the-art in both computational speed and final surface error.en_US
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Image-based rendering; Shape modeling; Machine learning
dc.subjectComputing methodologies → Image
dc.subjectbased rendering
dc.subjectShape modeling
dc.subjectMachine learning
dc.titleN-SfC: Robust and Fast Shape Estimation from Caustic Imagesen_US
dc.description.seriesinformationVision, Modeling, and Visualization
dc.description.sectionheadersRendering and Modelling
dc.identifier.doi10.2312/vmv.20231224
dc.identifier.pages33-41
dc.identifier.pages9 pages


Files in this item

Thumbnail
Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International License
Except where otherwise noted, this item's license is described as Attribution 4.0 International License