Geometry-aware generation of adversarial point clouds

Y Wen, J Lin, K Chen, CLP Chen… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Machine learning models have been shown to be vulnerable to adversarial examples. While
most of the existing methods for adversarial attack and defense work on the 2D image …

Evolving a psycho-physical distance metric for generative design exploration of diverse shapes

S Khan, E Gunpinar… - Journal of …, 2019 - asmedigitalcollection.asme.org
In this paper, a generative design approach is proposed that involves the users'
psychological aspect in the design space exploration stage to create distinct design …

Polygons, points, or voxels? stimuli selection for crowdsourcing aesthetics preferences of 3D shape pairs

K Dev, N Villar, M Lau - … of the symposium on Computational Aesthetics, 2017 - dl.acm.org
Visual aesthetics is one of the fundamental perceptual properties of 3D shapes. Since the
perception of shape aesthetics can be subjective, we take a data-driven approach and …

[KNIHA][B] Data-Driven Modelling of Perceptual Properties of 3D Shapes

K Dev - 2018 - search.proquest.com
The recent surge in 3D content generation has led to the evolution of difficult to search,
organise and re-use massive online 3D visual content libraries. We explore crowdsourcing …