Title | ||
---|---|---|
Data-driven method for sketch-based 3D shape retrieval based on user similar draw-style recommendation. |
Abstract | ||
---|---|---|
Sketching is a simple and natural way of expression and communication for humans. It also gains increasing popularity in human computer interaction, with the emergence of multitouch tablets and styluses. The main characteristics of sketches can be summarized in two aspects: (i) the fuzziness of the sketch information, which can be attributed to that the completeness of the sketch is evolving with the drawing process and there is no fixed mapping between the user expression and the sketch; (ii) the randomness of user input, arising from that users' input is not only associated with their field background, way of thinking, hand-painted habits and preferences, but also affected by types of equipments and environmental factors. These two characteristics make the sketch can express creative thinking, but it is also the two characteristics that make the freehand sketch recognition algorithm must have enough robustness to support user interaction. Neglecting the above two issues in previous studies causes the results to be less satisfactory. In recent years, sketch-based interactive methods are widely used in many retrieval systems. In particular, a variety of sketch-based 3D model retrieval works have been presented. However, almost all these works focus on directly matching sketches with the projection views of 3D models, and they suffer from the large differences between the sketch drawing and the views of 3D models, leading to unsatisfying retrieval results. Therefore, in this article, during the matching procedure in the retrieval, we propose to match the sketch with the ones of each 3D model from historical users instead of projection views. Yet since the sketches between the current user and the historical users can have big difference, we also study appropriate methods to handle users' personalized deviations and differences. To this end, we leverage recommendation algorithms to estimate the drawing style characteristic similarity between the current user and historical users. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1145/3005274.3005314 | SIGGRAPH Asia Posters |
Field | DocType | Citations |
Computer vision,Data-driven,Computer graphics (images),Computer science,Popularity,Creative thinking,Robustness (computer science),Sketch recognition,Artificial intelligence,Completeness (statistics),Randomness,Sketch | Conference | 0 |
PageRank | References | Authors |
0.34 | 1 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Fei Wang | 1 | 241 | 51.35 |
Shujin Lin | 2 | 77 | 7.74 |
Hefeng Wu | 3 | 90 | 14.67 |
Ruomei Wang | 4 | 35 | 20.82 |
Xiaonan Luo | 5 | 697 | 92.76 |