VideoMatte240K consists of 484 high-resolution green screen videos and generate a total of 240,709 unique frames of alpha mattes and foregrounds with chroma-key software Adobe After Effects. The videos are purchased as stock footage or found as royalty-free materials online. 384 videos are at 4K resolution and 100 are in HD. The videos are split by 479 : 5 to form the train and validation sets. The dataset consists of a vast amount of human subjects, clothing, and poses that are helpful for training robust models.
10 PAPERS • NO BENCHMARKS YET
VideoMatting108 is a large-scale video matting and trimap generation dataset with 80 training and 28 validation foreground video clips with ground-truth alpha mattes.
3 PAPERS • NO BENCHMARKS YET
PhotoMatte85 contains 85 protrait images. The dataset is donated to us by a third-party commercial company. The footage are shot with professional studio lighting and the subjects are in standard portrait posing. We provide the alpha matte and foreground images extracted from the green screen photos. Due to license issue, we will not release the other 13K images used in training.
1 PAPER • NO BENCHMARKS YET