DifferSketching: How Differently Do People Sketch 3D Objects?
DescriptionMultiple sketch datasets have been proposed to understand how people draw 3D objects. However, such datasets are often of small scale and cover a small set of objects or categories. In addition, these datasets contain freehand sketches mostly from expert users, making it difficult to compare the drawings by expert and novice users, while such comparisons will potentially help design more effective sketch-based interfaces for specific or both groups of users. These observations motivate us to analyze how differently people with and without good drawing skills sketch 3D objects. We invited 70 novice users and 38 expert users to sketch 136 3D objects, which were presented as 362 images rendered from multiple views. This leads to a new dataset of 3,620 freehand multi-view sketches, which are registered with the corresponding 3D objects under certain views. Our dataset is an order of magnitude larger than the existing datasets. We analyze the collected data at three levels, i.e., sketch-level, stroke-level, and pixel-level, in both spatial and
temporal characteristics, and within and across groups of creators. We found that the drawings by professionals and novices show significant differences in the stroke-level, both intrinsically and extrinsically. We demonstrate the usefulness of our dataset in two applications: freehand sketch synthesis and using it as a potential benchmark for sketch-based 3D reconstruction.
Event Type
Technical Papers
TimeFriday, 9 December 202210:30am - 12:00pm KST
Registration Categories