Pic2PolyArt: Transforming a photograph into polygon-based geometric art

作者：

Highlights：

• We proposed a novel, subject-focused geometric abstraction framework that can support both triangle-based and polygon-based abstraction.

• Photo subject extraction is performed using a combination of saliency detection, edge detection and face detection techniques.

• Qualitative intrinsic quality evaluation is performed on benchmark stylization dataset.

• Empirical user studies are also performed to evaluate the effectiveness of this model.

摘要

•We proposed a novel, subject-focused geometric abstraction framework that can support both triangle-based and polygon-based abstraction.•Photo subject extraction is performed using a combination of saliency detection, edge detection and face detection techniques.•Qualitative intrinsic quality evaluation is performed on benchmark stylization dataset.•Empirical user studies are also performed to evaluate the effectiveness of this model.

论文关键词：Geometric art,Computational art,Low poly rendering,Style transfer,Non-photorealistic rendering

论文评审过程：Received 15 January 2020, Revised 19 September 2020, Accepted 27 November 2020, Available online 1 December 2020, Version of Record 11 December 2020.

论文官网地址：https://doi.org/10.1016/j.image.2020.116090