Learning to complete 3D scenes from single depth images
Building a complete 3D model of a scene given only a single depth image is underconstrained. To acquire a full volumetric model, one typically needs either multiple views, or a single view together with a library of unambiguous 3D models that will fit the shape of each individual object in the scene...
Main Author: | |
---|---|
Other Authors: | |
Published: |
University College London (University of London)
2016
|
Subjects: | |
Online Access: | https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.763151 |