Back

Creative Flow+ Dataset

Large densely annotated artistic video dataset

Creative Flow+ Dataset

We present the Creative Flow+ Dataset, the first diverse multi-style artistic video dataset richly labeled with per-pixel optical flow, occlusions, correspondences, segmentation labels, normals, and depth. Our dataset includes 3000 animated sequences rendered using styles randomly selected from 40 textured line styles and 38 shading styles, spanning the range between flat cartoon fill and wildly sketchy shading. Our dataset includes 124K+ train set frames and 10K test set frames rendered at 1500x1500 resolution, far surpassing the largest available optical flow datasets in size. While modern techniques for tasks such as optical flow estimation achieve impressive performance on realistic images and video, today there is no way to gauge their performance on non-photorealistic images. Creative Flow+ poses a new challenge to generalize real-world Computer Vision to messy stylized content.

View this Dataset
->
View author website
Task
Image Classification
Annotation Types
Semantic Segmentation
124000
Items
50
Classes
124000
Labels
Models using this dataset
Last updated on 
January 20, 2022
Licensed under 
Unknown