Enabling Viewpoint Learning through Dynamic Label Generation

Simple item page
dc.contributor.authorSchelling, Michaelen_US
dc.contributor.authorHermosilla, Pedroen_US
dc.contributor.authorVázquez, Pere-Pauen_US
dc.contributor.authorRopinski, Timoen_US
dc.contributor.editorMitra, Niloy and Viola, Ivanen_US
dc.date.accessioned2021-04-09T08:01:06Z
dc.date.available2021-04-09T08:01:06Z
dc.date.issued2021
dc.description.abstractOptimal viewpoint prediction is an essential task in many computer graphics applications. Unfortunately, common viewpoint qualities suffer from two major drawbacks: dependency on clean surface meshes, which are not always available, and the lack of closed-form expressions, which requires a costly search involving rendering. To overcome these limitations we propose to separate viewpoint selection from rendering through an end-to-end learning approach, whereby we reduce the influence of the mesh quality by predicting viewpoints from unstructured point clouds instead of polygonal meshes. While this makes our approach insensitive to the mesh discretization during evaluation, it only becomes possible when resolving label ambiguities that arise in this context. Therefore, we additionally propose to incorporate the label generation into the training procedure, making the label decision adaptive to the current network predictions. We show how our proposed approach allows for learning viewpoint predictions for models from different object categories and for different viewpoint qualities. Additionally, we show that prediction times are reduced from several minutes to a fraction of a second, as compared to state-of-the-art (SOTA) viewpoint quality evaluation. Code and training data is available at https://github.com/schellmi42/viewpoint_learning, which is to our knowledge the biggest viewpoint quality dataset available.en_US
dc.description.number2
dc.description.sectionheadersVisualization
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume40
dc.identifier.doi10.1111/cgf.142643
dc.identifier.issn1467-8659
dc.identifier.pages413-423
dc.identifier.urihttps://doi.org/10.1111/cgf.142643
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf142643
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectComputing methodologies
dc.subjectComputer graphics
dc.subjectNeural networks
dc.titleEnabling Viewpoint Learning through Dynamic Label Generationen_US
Files
Original bundle
Now showing 1 - 3 of 3
Thumbnail Image
Name:
v40i2pp413-423.pdf
Size:
20.36 MB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
paper1014_supp.pdf
Size:
1.64 MB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
cgf40-2_142643_ProjektDeal.pdf
Size:
20.44 MB
Format:
Adobe Portable Document Format
Description:
Projekt Deal version
Download
Collections
40-Issue 2