Show simple item record

dc.contributor.authorJeon, Junhoen_US
dc.contributor.authorJung, Jinwoongen_US
dc.contributor.authorKim, Jungeonen_US
dc.contributor.authorLee, Seungyongen_US
dc.contributor.editorFu, Hongbo and Ghosh, Abhijeet and Kopf, Johannesen_US
dc.date.accessioned2018-10-07T14:57:43Z
dc.date.available2018-10-07T14:57:43Z
dc.date.issued2018
dc.identifier.issn1467-8659
dc.identifier.urihttps://doi.org/10.1111/cgf.13544
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf13544
dc.description.abstractSemantic segmentation partitions a given image or 3D model of a scene into semantically meaning parts and assigns predetermined labels to the parts. With well-established datasets, deep networks have been successfully used for semantic segmentation of RGB and RGB-D images. On the other hand, due to the lack of annotated large-scale 3D datasets, semantic segmentation for 3D scenes has not yet been much addressed with deep learning. In this paper, we present a novel framework for generating semantically segmented triangular meshes of reconstructed 3D indoor scenes using volumetric semantic fusion in the reconstruction process. Our method integrates the results of CNN-based 2D semantic segmentation that is applied to the RGB-D stream used for dense surface reconstruction. To reduce the artifacts from noise and uncertainty of single-view semantic segmentation, we introduce adaptive integration for the volumetric semantic fusion and CRF-based semantic label regularization. With these methods, our framework can easily generate a high-quality triangular mesh of the reconstructed 3D scene with dense (i.e., per-vertex) semantic labels. Extensive experiments demonstrate that our semantic segmentation results of 3D scenes achieves the state-of-the-art performance compared to the previous voxel-based and point cloud-based methods.en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectComputing methodologies
dc.subjectReconstruction
dc.subjectScene understanding
dc.titleSemantic Reconstruction: Reconstruction of Semantically Segmented 3D Meshes via Volumetric Semantic Fusionen_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersRegistration and Reconstruction
dc.description.volume37
dc.description.number7
dc.identifier.doi10.1111/cgf.13544
dc.identifier.pages25-35


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

  • 37-Issue 7
    Pacific Graphics 2018 - Symposium Proceedings

Show simple item record