TY  - JOUR
A1  - Rosin, Paul L.
A1  - Lai, Yu-Kun
A1  - Mould, David
A1  - Yi, Ran
A1  - Berger, Itamar
A1  - Doyle, Lars
A1  - Lee, Seungyong
A1  - Li, Chuan
A1  - Liu, Yong-Jin
A1  - Semmo, Amir
A1  - Shamir, Ariel
A1  - Son, Minjung
A1  - Winnemöller, Holger
T1  - NPRportrait 1.0: A three-level benchmark for non-photorealistic rendering of portraits
JF  - Computational visual media
N2  - Recently, there has been an upsurge of activity in image-based non-photorealistic rendering (NPR), and in particular portrait image stylisation, due to the advent of neural style transfer (NST). However, the state of performance evaluation in this field is poor, especially compared to the norms in the computer vision and machine learning communities. Unfortunately, the task of evaluating image stylisation is thus far not well defined, since it involves subjective, perceptual, and aesthetic aspects. To make progress towards a solution, this paper proposes a new structured, three-level, benchmark dataset for the evaluation of stylised portrait images. Rigorous criteria were used for its construction, and its consistency was validated by user studies. Moreover, a new methodology has been developed for evaluating portrait stylisation algorithms, which makes use of the different benchmark levels as well as annotations provided by user studies regarding the characteristics of the faces. We perform evaluation for a wide variety of image stylisation methods (both portrait-specific and general purpose, and also both traditional NPR approaches and NST) using the new benchmark dataset.
KW  - non-photorealistic rendering (NPR)
KW  - image stylization
KW  - style transfer
KW  - portrait
KW  - evaluation
KW  - benchmark
Y1  - 2022
U6  - https://doi.org/10.1007/s41095-021-0255-3
SN  - 2096-0433
SN  - 2096-0662
VL  - 8
IS  - 3
SP  - 445
EP  - 465
PB  - Springer Nature
CY  - London
ER  -