Instance-Aware Coherent Video Style Transfer for Chinese Ink Wash Painting

Authors: Hao Liang, Shuai Yang, Wenjing Wang, Jiaying Liu

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

Reproducibility Variable Result LLM Response
Research Type Experimental 4 Experimental Results For training, we use Chinese ink wash paintings in Chip Phi dataset [He et al., 2018], and further collect 115 videos of horses from the Internet, about 10k frames in total. PWCNet [Niklaus, 2019; Sun et al., 2018] is used to estimate optical flows for training and testing. More experimental details and results are provided in the supplementary material.
Researcher Affiliation Academia Wangxuan Institute of Computer Technology, Peking University {lianghao17, williamyang, daooshee, liujiaying}@pku.edu.cn
Pseudocode No No structured pseudocode or algorithm blocks were found in the paper.
Open Source Code No The paper states: "Our project website is available at https://oblivioussy.github.io/Ink Video/." This is a project website, not an explicit direct link to a source code repository for the methodology.
Open Datasets Yes For training, we use Chinese ink wash paintings in Chip Phi dataset [He et al., 2018], and further collect 115 videos of horses from the Internet, about 10k frames in total.
Dataset Splits No The paper mentions using a dataset for training but does not provide specific percentages or counts for training, validation, and test splits.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types, or memory amounts) used for running its experiments.
Software Dependencies No The paper mentions using 'PWCNet' and cites its reimplementation using 'PyTorch' in the reference section, but it does not provide specific version numbers for PyTorch or other software dependencies.
Experiment Setup No The paper states 'More experimental details and results are provided in the supplementary material', but does not include specific hyperparameter values or detailed training configurations within the main text.