410 likes | 544 Views
Structure and Aesthetics in Non-Photorealistic Images. Hua Li, David Mould, and Jim Davies Carleton University. Artistic or Messed. 2 /35. Related Work on Evaluating Non-Photorealistic Algorithms. Performance based on processing speed ill-suited for stylization
E N D
Structure and Aesthetics in Non-Photorealistic Images Hua Li, David Mould, and Jim Davies Carleton University
Artistic or Messed 2/35
Related Work on Evaluating Non-Photorealistic Algorithms • Performance based on processing speed • ill-suited for stylization • Side-by-side comparisons • not fully convinced by audience 3/35
Perceptual Evaluation on Non-Photorealistic Algorithms • Quantitative evaluation • rating scores [Schumann et al. 96, Gooch and Willemsen 02, Mandryk et al. 2011, Mould et al. 2012] • response time [Gooch et al. 04] • eye-tracking data [Mandryk et al. 2011, Mould et al. 2012] • Qualitative evaluation • questionnaire-based 4/35
Motivation of Our StudyTone Structure [Floyd and Steinberg 76] [Ostromoukhov 01] [Qu et al. 08] [Ours 11] 5/35
Questions to Answer • Are structural and aesthetic quality related? • Do images matter for side-by-side comparisons? 6/35
Participants • 30 participants • 15 female and 15 male • 11 artists • aged 18 to 33 7/35
Study Overview • 1 ~ 1.5 hours to complete the experiment • Using the keyboard or the mouse to enter their responses • Tasks: • rating structural and aesthetic quality • collecting response times for rendered images 8/35
Image Stimuli • Seven categories • include cars, cats, persons, flowers, buildings, mugs, and birds. • Each category contains 13 different images including • one unprocessed image • and 12 rendered images using 12 algorithms. • Images are black and white, or greyscale to remove the influence of color. 9/36
Procedure • Step 1: verbal introduction • Step 2: training • Step 3: formal study • Step 4: questionnaire • Step 5: ranking 10/35
Interfaces Used 11/35 Interface for collecting the response time
Interfaces Used Aesthetic rating Structural rating 12/35
Experimental Images -Bird Category Unprocessed 13/35
Experimental Images - Bird Category Structure-Aware Structure-Preserving Stippling (SPS) 14/35
Experimental Images - Bird Category Structure-Aware Content-Sensitive Screening (CSS) 15/35
Experimental Images - Bird Category Structure-Aware SPS with Exclusion Masks (SPH) 16/35
Experimental Images - Bird Category Structure-Aware Line Art using edge tangent field (ETF) 17/35
Experimental Images - Bird Category Structure-Aware Artistic Tessellation (AT) 18/35
Experimental Images - Bird Category Structure-Aware Line Art from SPS (Drawing) 19/35
Experimental Images - Bird Category Tone-based Secord’s Stippling Method (Secord) 20/35
Experimental Images - Bird Category Tone-based Line Art using edge tangent field (Mmosaics) 21/35
Experimental Images - Bird Category Contrast-Aware Halftoning (CAH) 22/35
Experimental Images - Bird Category Black and White (BW) 23/35
Experimental Images - Bird Category Reduced Information Adding 50% salt and pepper noise (Noisy) 24/35
Experimental Images - Bird Category Reduced Information Gaussian filter (Blurring) 25/35
Positive Correlation Between Structural and Aesthetic Ratings 26/35
Dot-based Methods (Stippling) Tone-based Structure-Aware Structure-Aware Tone-based 27/35
Region-based Methods (Mosaics) Tone-based Structure-Aware Structure-Aware Tone-based 28/35
Effect of Category on Response Time Building < Flower < Bird < Cat < Person < Mug < Car 30/35
Artists and Non-Artists 31/35
Overall Ranks after Study • Participants preferred the AT images (7/30 responses) the most, CAH second (6/30). • Participants’ least favorite • blurred images most often (20/30 responses), and with AT second (5/30). • Controversial ranking for stylized images rendered by the AT method. 32/35
Conclusions • Considering structure as a possible way to increase aesthetic appeal. • Considering the choice of the images used. • Generally, bird images were the easiest images to abstract, while Person images were the most difficult. 33/35
Future Work • More Participants • More Categories • More NPR Algorithms • Eye tracker 34/35
Thanks for Your Attention. Questions? 35/35
Interaction between Categories and Algorithms (skip) Aesthetic scores 38/41