Sie sind hier: Startseite Kolloquium Understanding 3D Scans

Understanding 3D Scans

Prof. Dr. Angela Dai, TU München

Art des Termins
    Wann 21.12.2020
    von 16:00 bis 17:30
    Wo Zoom-Session
    Termin übernehmen vCal

    With recent developments in both commodity range sensors as well as mixed reality devices, capturing and creating 3D models of the world around us has become increasingly important. As the world around us lives in a three-dimensional space, such 3D models will not only facilitate capture and display for content creation but also provide a basis for fundamental scene understanding, from semantic understanding to virtual interactions, which must be formulated in 3D for many applications such as augmented or virtual reality. My talk will focus on constructing a generative formulation for the construction of 3D models from RGB-D data, and the use of 3D reconstructions towards a 3D semantic and instance understanding of these scenes. I will begin with the capture and reconstruction of RGB-D scan data, and discuss two major challenges towards construction of semantically meaningful 3D content: inferring 3D semantic understanding (by way of semantic and instance segmentation), and generating high-quality 3D model geometry. I will present 3D deep learning approaches based on the 3D, RGB-D nature of these scans, to predict spatially consistent semantic and instance segmentations of 3D scenes, along with generating the complete geometry of a partially observed scene. This enables first steps towards democratization of content creation and 3D understanding.