NPRportrait 1.0: A Three-Level Benchmark for Non-Photorealistic Rendering of Portraits

Despite the recent upsurge of activity in image-based non-photorealistic rendering (NPR), and in particular portrait image stylisation, due to the advent of neural style transfer, the state of performance evaluation in this field is limited, 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 neural style transfer) using the new benchmark dataset.

Improving the Quality of Non-Holonomic Motion by Hybridizing C-PRM Paths

Sampling-based motion planners are an effective means for generating collision-free motion paths. However, the quality of these motion paths, with respect to different quality measures such as path length, clearance, smoothness or energy, is often notoriously low. This problem is accentuated in the case of non-holonomic sampling-based motion planning, in which the space of feasible motion trajectories is restricted. In this study, we combine the C-PRM algorithm by Song and Amato with our recently introduced path-hybridization approach, for creating high quality non-holonomic motion paths, with combinations of several different quality measures such as path length, smoothness or clearance, as well as the number of reverse car motions. Our implementation includes a variety of code optimizations that result in nearly real-time performance, and which we believe can be extended with further optimizations to a real-time tool for the planning of high-quality car-like motion.