arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.06133cs.CVcs.LGcs.MM
收藏

基于草图的深度建模:提示和技巧

Deep Sketch-Based Modeling: Tips and Tricks

University of Surrey(萨里大学);Beijing University of Posts and Telecommunications(北京邮电大学);iFlyTek-Surrey Joint Research Centre on Artificial Intelligence(科大讯飞-萨里大学人工智能联合研究中心)

Yue Zhong, Yulia Gryaditskaya, Honggang Zhang, Yi-Zhe Song

摘要:

基于深度图像的建模近年来受到了广泛的关注,但基于草图的建模的并行问题只得到了简要的研究,通常作为一个潜在的应用。在这项工作中,我们第一次确定了草图和图像输入之间的主要区别:(i)风格差异,(ii)不精确的视角,以及(iii)稀疏性。我们讨论了为什么这些差异中的每一个都可能构成挑战,甚至使某一类基于图像的方法不适用。我们研究替代解决方案,以解决每个差异。通过这样做,我们得出了一些重要的见解:(i)稀疏性通常会导致对前景与背景的不正确预测,(ii)人类风格的多样性,如果不考虑在内,可能会导致非常差的泛化性能,最后(iii)除非使用专用的草图界面,否则不能期望草图与固定视点的透视图相匹配。最后,我们比较了一组具有代表性的深度单图像建模解决方案,并展示了如何通过考虑已识别的关键差异来提高其性能以处理草图输入。

英文摘要:

Deep image-based modeling received lots of attention in recent years, yet the parallel problem of sketch-based modeling has only been briefly studied, often as a potential application. In this work, for the first time, we identify the main differences between sketch and image inputs: (i) style variance, (ii) imprecise perspective, and (iii) sparsity. We discuss why each of these differences can pose a challenge, and even make a certain class of image-based methods inapplicable. We study alternative solutions to address each of the difference. By doing so, we drive out a few important insights: (i) sparsity commonly results in an incorrect prediction of foreground versus background, (ii) diversity of human styles, if not taken into account, can lead to very poor generalization properties, and finally (iii) unless a dedicated sketching interface is used, one can not expect sketches to match a perspective of a fixed viewpoint. Finally, we compare a set of representative deep single-image modeling solutions and show how their performance can be improved to tackle sketch input by taking into consideration the identified critical differences.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑