3D Reconstruction from Sketch with Hidden Lines by Two-Branch Diffusion Model

Simple item page
dc.contributor.authorFukushima, Yutaen_US
dc.contributor.authorQi, Anranen_US
dc.contributor.authorShen, I-Chaoen_US
dc.contributor.authorGryaditskaya, Yuliaen_US
dc.contributor.authorIgarashi, Takeoen_US
dc.contributor.editorHu, Ruizhenen_US
dc.contributor.editorCharalambous, Panayiotisen_US
dc.date.accessioned2024-04-30T08:19:26Z
dc.date.available2024-04-30T08:19:26Z
dc.date.issued2024
dc.description.abstractWe present a method for sketch-based modelling of 3D man-made shapes that exploits not only the commonly considered visible surface lines but also the hidden lines typical for technical drawings. Hidden lines are used by artists and designers to communicate holistic shape structure. Given a single viewpoint sketch, leveraging such lines allows us to resolve the ambiguity of the shape's surfaces hidden from the observer. We assume that the separation into visible and hidden lines is given, and focus solely on how to leverage this information. Our strategy is to mingle two distinct diffusion networks: one generates denoized occupancy grid estimates from a visible line image, whilst the other generates occupancy grid estimates based on contextualized hidden lines unveiling the occluded shape structure. We iteratively merge noisy estimates from both models in a reverse diffusion process. Importantly, we demonstrate the importance of what we call a contextualized hidden lines image over just a hidden lines image. Our contextualized hidden lines image contains hidden lines and silhouette lines. Such contextualization allows us to achieve superior performance to a range of alternative configurations and reconstruct hidden holes and hidden surfaces.en_US
dc.description.sectionheadersGeometry and Modeling
dc.description.seriesinformationEurographics 2024 - Short Papers
dc.identifier.doi10.2312/egs.20241032
dc.identifier.isbn978-3-03868-237-0
dc.identifier.issn1017-4656
dc.identifier.pages4 pages
dc.identifier.urihttps://doi.org/10.2312/egs.20241032
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/egs20241032
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 → Artificial intelligence; Computer graphics → Shape modeling
dc.subjectComputing methodologies → Artificial intelligence
dc.subjectComputer graphics → Shape modeling
dc.title3D Reconstruction from Sketch with Hidden Lines by Two-Branch Diffusion Modelen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
17_egs20241032.pdf
Size:
21.28 MB
Format:
Adobe Portable Document Format
Download
Collections
EG 2024 - Short Papers