Mathias Eitz, Kristian Hildebrand, Tamy Boubekeur, and Marc Alexa ACM SIGGRAPH 2010 - Talk Program
From a simple user sketch, our 3D search engine can retrieve 3D models accurately, with instant feedback over massive 3D databases and handles naturally partial matching.
Abstract
As large collections of 3D models are starting to become as com-
mon as public image collections, the need arises to quickly locate
models in such collections. Models are often insufficiently anno-
tated such that a keyword based search is not promising. Our ap-
proach for content based searching of 3D models relies entirely on
visual analysis and is based on the observation that a large part of
our perception of shapes stems from their salient features, usually
captured by dominant lines in their display. Recent research on such
feature lines has shown that 1) people mostly draw the same lines
when asked to depict a certain model and 2) the shape of an object
is well represented by the set of feature lines generated by recent
NPR line drawing algorithms. Consequently, we
suggest an image based approach for 3D shape retrieval, exploit-
ing the similarity of human sketches and the results of current line
drawing algorithms. Our search engine takes a sketch of the desired
model drawn by a user as the input and compares this sketch to a
set of line drawings automatically generated for each of the models
in the collection.
BibTex Reference @InProceedings{Eitz:2010:SBSR,
author = {Mathias Eitz, Kristian Hildebrand, Tamy Boubekeur and Marc Alexa},
title = {Sketch-Based 3D Shape Retrieval},
booktitle ={ACM SIGGRAPH 2010 Talk Program},
year = {2010}
}
(full presentation)
.