Category‐Specific Salient View Selection via Deep Convolutional Neural Networks

dc.contributor.authorKim, Seong‐heumen_US
dc.contributor.authorTai, Yu‐Wingen_US
dc.contributor.authorLee, Joon‐Youngen_US
dc.contributor.authorPark, Jaesiken_US
dc.contributor.authorKweon, In Soen_US
dc.contributor.editorChen, Min and Zhang, Hao (Richard)en_US
dc.date.accessioned2018-01-10T07:42:58Z
dc.date.available2018-01-10T07:42:58Z
dc.date.issued2017
dc.description.abstractIn this paper, we present a new framework to determine up front orientations and detect salient views of 3D models. The salient viewpoint to human preferences is the most informative projection with correct upright orientation. Our method utilizes two Convolutional Neural Network (CNN) architectures to encode category‐specific information learnt from a large number of 3D shapes and 2D images on the web. Using the first CNN model with 3D voxel data, we generate a CNN shape feature to decide natural upright orientation of 3D objects. Once a 3D model is upright‐aligned, the front projection and salient views are scored by category recognition using the second CNN model. The second CNN is trained over popular photo collections from internet users. In order to model comfortable viewing angles of 3D models, a category‐dependent prior is also learnt from the users. Our approach effectively combines category‐specific scores and classical evaluations to produce a data‐driven viewpoint saliency map. The best viewpoints from the method are quantitatively and qualitatively validated with more than 100 objects from 20 categories. Our thumbnail images of 3D models are the most favoured among those from different approaches.In this paper, we present a new framework to determine up front orientations and detect salient views of 3D models. The salient viewpoint to human preferences is the most informative projection with correct upright orientation. Our method utilizes two Convolutional Neural Network (CNN) architectures to encode category‐specific information learnt from a large number of 3D shapes and 2D images on the web. Using the first CNN model with 3D voxel data, we generate a CNN shape feature to decide natural upright orientation of 3D objects. Once a 3D model is upright‐aligned, the front projection and salient views are scored by category recognition using the second CNN model. The second CNN is trained over popular photo collections from internet users. In order to model comfortable viewing angles of 3D models, a category dependent prior is also learnt from the users. Our approach effectively combines category‐specific scores and classical evaluations to produce a data‐driven viewpoint saliency map. The best viewpoints from the method are quantitatively and qualitatively validated with more than 100 objects from 20 categories. Our thumbnail images of 3D models are the most favored among those from different approaches.en_US
dc.description.number8
dc.description.sectionheadersArticles
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume36
dc.identifier.doi10.1111/cgf.13082
dc.identifier.issn1467-8659
dc.identifier.pages313-328
dc.identifier.urihttps://doi.org/10.1111/cgf.13082
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf13082
dc.publisher© 2017 The Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectbest view selection
dc.subjectupright orientation estimation
dc.subjectdeep learning
dc.subjectCategories and Subject Descriptors (according to ACM CCS): I.3.3 [Computer Graphics]: Picture/Image Generation—Display algorithms
dc.subjectViewing algorithms I.5.1 [Pattern Recognition]: Models—Neural Nets
dc.titleCategory‐Specific Salient View Selection via Deep Convolutional Neural Networksen_US
Files
Collections