Learning 3D Scene Synthesis from Annotated RGB-D Images

dc.contributor.authorKermani, Zeinab Sadeghipouren_US
dc.contributor.authorLiao, Zichengen_US
dc.contributor.authorTan, Pingen_US
dc.contributor.authorZhang, Hao (Richard)en_US
dc.contributor.editorMaks Ovsjanikov and Daniele Panozzoen_US
dc.date.accessioned2016-06-17T14:12:08Z
dc.date.available2016-06-17T14:12:08Z
dc.date.issued2016en_US
dc.description.abstractWe present a data-driven method for synthesizing 3D indoor scenes by inserting objects progressively into an initial, possibly, empty scene. Instead of relying on few hundreds of hand-crafted 3D scenes, we take advantage of existing large-scale annotated RGB-D datasets, in particular, the SUN RGB-D database consisting of 10,000+ depth images of real scenes, to form the prior knowledge for our synthesis task. Our object insertion scheme follows a co-occurrence model and an arrangement model, both learned from the SUN dataset. The former elects a highly probable combination of object categories along with the number of instances per category while a plausible placement is defined by the latter model. Compared to previous works on probabilistic learning for object placement, we make two contributions. First, we learn various classes of higher-order objectobject relations including symmetry, distinct orientation, and proximity from the database. These relations effectively enable considering objects in semantically formed groups rather than by individuals. Second, while our algorithm inserts objects one at a time, it attains holistic plausibility of the whole current scene while offering controllability through progressive synthesis. We conducted several user studies to compare our scene synthesis performance to results obtained by manual synthesis, stateof- the-art object placement schemes, and variations of parameter settings for the arrangement model.en_US
dc.description.number5en_US
dc.description.sectionheadersStructuresen_US
dc.description.seriesinformationComputer Graphics Forumen_US
dc.description.volume35en_US
dc.identifier.doi10.1111/cgf.12976en_US
dc.identifier.issn1467-8659en_US
dc.identifier.pages197-206en_US
dc.identifier.urihttps://doi.org/10.1111/cgf.12976en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectI.3.5 [Computer Graphics]en_US
dc.subjectComputational Geometry and Object Modelingen_US
dc.titleLearning 3D Scene Synthesis from Annotated RGB-D Imagesen_US
Files