Noisy Imperfect Partial Symbolic Sketches

The Noisy Imperfect Partial Symbolic Sketches (NIPSS) dataset provides symbolic sketches generated from the texture extraction method described in [1] when the inputs are associated with, either Imagenet animals [2] that have been preprocessed by [3], or the CelebAMask-HQ person faces described in [4].Any sketch is an image containing a multichannel (artificial color) binary sequence of information, where artificial colors have consisted in concatenating the results of different regularizers from [1].[1] Abdourrahmane M. Atto and Grégoire Mercier, High order structural image decomposition by using non-linear and non-convex regularizing objectives, Computer Vision and Image Understanding, Volume 138, 2015, Pages 38-50, https://doi.org/10.1016/j.cviu.2015.04.002[2] J. Deng, W. Dong, R. Socher, L. -J. Li, Kai Li and Li Fei-Fei, ImageNet: A large-scale hierarchical image database, 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA, 2009, pp. 248-255, doi: 10.1109/CVPR.2009.5206848.[3] Haohan Wang and Songwei Ge and Eric P. Xing and Zachary C. Lipton, Learning Robust Global Representations by Penalizing Local Predictive Power, arXiv EPRINT 1905.13549, 2019.[4] Lee Cheng-Han and Liu Ziwei and Wu Lingyun and Luo Ping, MaskGAN: Towards Diverse and Interactive Facial Image Manipulation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.