Face Sketch Synthesis Style Similarity:A New Structure Co-occurrence Texture Measure
This work addresses a critical evaluation bottleneck in the face sketch synthesis field, enabling more reliable algorithm development.
The paper tackled the problem of unreliable similarity measures in face sketch synthesis, which are sensitive to slight image degradation and misalign with human perception, by proposing a new robust style similarity measure called Scoot-measure that evaluates block-level structure and texture; experimental results showed it achieved a 78.8% correlation with human judgment, outperforming the prior best measure at 58.6%.
Existing face sketch synthesis (FSS) similarity measures are sensitive to slight image degradation (e.g., noise, blur). However, human perception of the similarity of two sketches will consider both structure and texture as essential factors and is not sensitive to slight ("pixel-level") mismatches. Consequently, the use of existing similarity measures can lead to better algorithms receiving a lower score than worse algorithms. This unreliable evaluation has significantly hindered the development of the FSS field. To solve this problem, we propose a novel and robust style similarity measure called Scoot-measure (Structure CO-Occurrence Texture Measure), which simultaneously evaluates "block-level" spatial structure and co-occurrence texture statistics. In addition, we further propose 4 new meta-measures and create 2 new datasets to perform a comprehensive evaluation of several widely-used FSS measures on two large databases. Experimental results demonstrate that our measure not only provides a reliable evaluation but also achieves significantly improved performance. Specifically, the study indicated a higher degree (78.8%) of correlation between our measure and human judgment than the best prior measure (58.6%). Our code will be made available.