N-SfC: Robust and Fast Shape Estimation from Caustic Images
| dc.contributor.author | Kassubeck, Marc | en_US |
| dc.contributor.author | Kappel, Moritz | en_US |
| dc.contributor.author | Castillo, Susana | en_US |
| dc.contributor.author | Magnor, Marcus | en_US |
| dc.contributor.editor | Guthe, Michael | en_US |
| dc.contributor.editor | Grosch, Thorsten | en_US |
| dc.date.accessioned | 2023-09-25T11:36:40Z | |
| dc.date.available | 2023-09-25T11:36:40Z | |
| dc.date.issued | 2023 | |
| dc.description.abstract | This 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.description.sectionheaders | Rendering and Modelling | |
| dc.description.seriesinformation | Vision, Modeling, and Visualization | |
| dc.identifier.doi | 10.2312/vmv.20231224 | |
| dc.identifier.isbn | 978-3-03868-232-5 | |
| dc.identifier.pages | 33-41 | |
| dc.identifier.pages | 9 pages | |
| dc.identifier.uri | https://doi.org/10.2312/vmv.20231224 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.2312/vmv20231224 | |
| dc.publisher | The Eurographics Association | en_US |
| dc.rights | Attribution 4.0 International License | |
| dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
| dc.subject | CCS Concepts: Computing methodologies → Image-based rendering; Shape modeling; Machine learning | |
| dc.subject | Computing methodologies → Image | |
| dc.subject | based rendering | |
| dc.subject | Shape modeling | |
| dc.subject | Machine learning | |
| dc.title | N-SfC: Robust and Fast Shape Estimation from Caustic Images | en_US |