Sketch Generation with Drawing Process Guided by Vector Flow and Grayscale

Authors: Zhengyan Tong, Xuanhong Chen, Bingbing Ni, Xiaohang Wang609-616

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Comparison with existing pencil drawing algorithms shows that our method is superior to others in terms of texture quality, style, and user evaluation.
Researcher Affiliation Collaboration Zhengyan Tong,1 Xuanhong Chen,1,2 Bingbing Ni,1,2* Xiaohang Wang 1 1 Shanghai Jiao Tong University 2 Huawei Hisilicon
Pseudocode No The paper describes algorithmic steps in text and figures but does not contain structured pseudocode or algorithm blocks.
Open Source Code Yes Our code and supplementary material are now available at: https://github.com/TZYSJTU/Sketch-Generation-with Drawing-Process-Guided-by-Vector-Flow-and-Grayscale
Open Datasets No The paper does not provide concrete access information (specific link, DOI, repository name, formal citation with authors/year, or reference to established benchmark datasets) for a publicly available or open dataset.
Dataset Splits No The paper refers to using input images and comparing results but does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) needed to reproduce the data partitioning.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers like Python 3.8, CPLEX 12.4) needed to replicate the experiment.
Experiment Setup Yes Usually, we fix W to be 5 pixels to get finer details. We fix the quantization order of direction to be 10 because too few directions will make the texture fluency worse, but too many directions will not improve the visual experience. The quantization order of gray level could be chosen from 8-16 according to the input.