NPRportrait 1 0 A Three Level Benchmark for Non Photorealistic Rendering of Portraits

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 . 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 users regarding the characteristics of the faces . We perform evaluation for a wide variety of image stylising methods (both portrait-specific and general purpose, and also both traditional NPR approaches and neural style transfer) using the new benchmark dataset . We use this benchmark dataset to test our ability to identify a wide range of different types of image styling methods. We use the benchmark dataset

Links: PDF - Abstract

Code :

None

Keywords : benchmark - dataset - portrait - image - evaluating -

Leave a Reply

Your email address will not be published. Required fields are marked *