maxwelljones14/

refVFX_dataset

This dataset is an unofficial reimplementation of the RefVFX project for tuning-free visual effect transfer across videos. The data and code were generated with the help of the arxiv paper and AI coding software. Original Paper: Tuning-free Visual Effect Transfer across Videos

	Dataset Statistics





	

Subset Effect Types Total Pairs Avg Pairs per Effect

Code-Based Edits 2736 136,800 50.0

Neural V2V 114 22,922… See the full description on the dataset page: https://huggingface.co/datasets/maxwelljones14/refVFX_dataset.