A paper develops a new shape model that allows synthesizing noveldistance views by optimizing a continuous signed directional distance function . Unlike an SDF, an SDDF measures distance in a given direction . This allows us to form a shape model without 3D shape supervision, using only distancemeasurements, readily available from depth camera or Lidar sensors . Our model removes post-processing steps like surface extraction or rendering by predicting distance at arbitrary locations and viewing directions . Our SDDF formulation can represent wholecategories of shapes and complete or interpolate across shapes from partial input data . Thisstructure constraint not only results in dimensionality reduction, but alsoprovides analytical confidence about the accuracy of SDDF predictions,regardless of the distance to the object surface. Our model also removes post processing steps likesurface extraction or renders . Our new model

Author(s) : Ehsan Zobeidi, Nikolay Atanasov

Links : PDF - Abstract

Code :
Coursera

Keywords : distance - model - shape - sddf - surface -

Leave a Reply

Your email address will not be published. Required fields are marked *