Perception-Driven Semi-Structured Boundary Vectorization

Shayan Hoshyari1, Edoardo A. Dominici1, Alla Sheffer1, Nathan Carr2, Duygu Ceylan2, Zhaowen Wang2, I-Chao Shen3

1 University of British Columbia, 2 Adobe, 3 National Taiwan University

Accepted to SIGGRAPH 2018

Vectorizing artist-drawn semi-structured raster images using existing methods results in visible artifacts. Our perception-driven vectorization output is consistent with viewer expectations. Please zoom in online to see details. Input image © aves --

Artist-drawn images with distinctly colored, piecewise continuous boundaries, which we refer to as semi-structured imagery, are very common in online raster databases and typically allow for a perceptually unambiguous mental vector interpretation. Yet, perhaps surprisingly, existing vectorization algorithms frequently fail to generate these viewer-expected interpretations on such imagery. In particular, the vectorized region boundaries they produce frequently diverge from those anticipated by viewers. We propose a new approach to region boundary vectorization that targets semi-structured inputs and leverages observations about human perception of shapes to generate vector images consistent with viewer expectations. When viewing raster imagery observers expect the vector output to be an accurate representation of the raster input. However, perception studies suggest that viewers implicitly account for the lossy nature of the rasterization process and mentally smooth and simplify the observed boundaries. Our core algorithmic challenge is to balance these conflicting cues and obtain a piecewise continuous vectorization whose discontinuities, or corners, are aligned with human expectations.
  Our framework centers around a simultaneous spline fitting and corner detection method that combines a learned metric, that approximates human perception of boundary discontinuities on raster inputs, with perception-driven algorithmic discontinuity analysis. The resulting method balances local cues provided by the learned metric with global cues obtained by balancing simplicity and continuity expectations. Given the finalized set of corners, our framework connects those using simple, continuous curves that capture input regularities. We demonstrate our method on a range of inputs and validate its superiority over existing alternatives via an extensive comparative user study.

@article{ hoshyari2018vectorization,	      
author    = {Hoshyari, Shayan and Alberto Dominici, Edoardo and Sheffer,
             Alla and Carr, Nathan and Ceylan, Duygu and Wang, Zhaowen
             and Shen, I-Chao},
title     = {Perception-Driven Semi-Structured Boundary Vectorization},
journal   = {ACM Transaction on Graphics},
year      = {2018},
volume    = {37},
number    = {4},
doi       = {10.1145/3197517.3201312},
publisher = {ACM},
address   = {New York, NY, USA},

Note: some of the input images shown are copyrighted by third parties and used with their permission. See the paper for the list of third-party sources.

All non-third-party images are © ACM.