Compared to the complete dataset of 250 classes built in Eitz et al. and Princeton Shape Benchmark (PSB) contains only 90 classes of 7200 sketches and 1258 models. However, even the large scale SHRECÂ’13 Sketch Track Benchmark (SHREC13STB) based on Eitz et al. They foster this research area by providing a small-scale and a large-scale sketch-based retrieval benchmark respectively and attracting state-of-the-art algorithms to participate and compete each other. In SHRECÂ’12 and SHRECÂ’13, two tracks have been successfully organized on the topic of sketch-based 3D model retrieval. Much less research work has been done regarding the Query-by-Sketch framework. However, most existing 3D model retrieval algorithms target the Query-by-Model framework which uses existing 3D models as queries. It is also popular and important for related applications such as sketch-based modeling and recognition, as well as 3D animation production via 3D reconstruction of a scene of 2D storyboard. This scheme is intuitive and convenient for users to learn and search for 3D models. Sketch-based 3D model retrieval is to retrieve relevant 3D models using sketch(es) as input.
The objective of this track is to evaluate the performances of different sketch-based 3D model retrieval algorithms using a large scale hand-drawn sketch query dataset on a generic 3D model dataset. We published an extended CVIU journal based on the SHREC'14 Sketch Track and Comprehensive Track! Please see the CVIU paper on the bottom.
0 kommentar(er)
