Learning Detail Transfer based on Geometric Features

Simple item page
dc.contributor.authorBerkiten, Semaen_US
dc.contributor.authorHalber, Maciejen_US
dc.contributor.authorSolomon, Justinen_US
dc.contributor.authorMa, Chongyangen_US
dc.contributor.authorLi, Haoen_US
dc.contributor.authorRusinkiewicz, Szymonen_US
dc.contributor.editorLoic Barthe and Bedrich Benesen_US
dc.date.accessioned2017-04-22T16:26:57Z
dc.date.available2017-04-22T16:26:57Z
dc.date.issued2017
dc.description.abstractThe visual richness of computer graphics applications is frequently limited by the difficulty of obtaining high-quality, detailed 3D models. This paper proposes a method for realistically transferring details (specifically, displacement maps) from existing high-quality 3D models to simple shapes that may be created with easy-to-learn modeling tools. Our key insight is to use metric learning to find a combination of geometric features that successfully predicts detail-map similarities on the source mesh; we use the learned feature combination to drive the detail transfer. The latter uses a variant of multi-resolution non-parametric texture synthesis, augmented by a high-frequency detail transfer step in texture space. We demonstrate that our technique can successfully transfer details among a variety of shapes including furniture and clothing.en_US
dc.description.number2
dc.description.sectionheadersReconstruct, Learn, and Transport Geometry
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume36
dc.identifier.doi10.1111/cgf.13132
dc.identifier.issn1467-8659
dc.identifier.pages361-373
dc.identifier.urihttps://doi.org/10.1111/cgf.13132
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf13132
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.titleLearning Detail Transfer based on Geometric Featuresen_US
Files
Original bundle
Now showing 1 - 3 of 3
No Thumbnail Available
Name:
v36i2pp361-373.pdf
Size:
22.01 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
supplemental_opt.pdf
Size:
7.11 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
video_final.m4v
Size:
52.35 MB
Format:
Unknown data format
Download
Collections
36-Issue 2