Creative Flow+ Dataset

large densely annotated artistic video dataset

including optical flow, occlusions, correspondences, segmentation labels, normals, and depth


Creative Flow+ Dataset challenges Computer Vision techniques to generalize to a wide range of styles, including messy stylized content. Our dataset is the first diverse multi-style artistic video dataset densely labeled with ground truth. Our synthetic dataset contains 3000 animated sequences (124K train and 10K test frames at 1500x1500) rendered in a wide range of artistic styles (40 line styles and 38 shading styles).


  author = {Shugrina, Maria and
    Liang, Ziheng and Kar, Amlan and Li, Jiaman and
    Singh, Angad and Singh, Karan and Fidler, Sanja},
  title = {Creative Flow+ Dataset},
  booktitle = {The IEEE Conference on Computer Vision
    and Pattern Recognition (CVPR)},
  month = {June},
  year = {2019}



Errata & Details


IMPORTANT: The links on this webpage are invalid until you click one of them to accept the user agreement.


Sequence Lists

Download these lists for navigating the data with our python utilities.

Rendering Packages

line alpha
These packages contain all visual renderings. Separate shading and line components of each composited stylized frame is also provided. Format: mp4 video files.

Flow Packages


These packages include forward flow, as special zip files, and occlusions, as mp4 clips.

Core Metadata Packages

normals (lossy)
corresp. (lossy)
depth (images)

These packages include core metadata, compression strategies vary (see errata).

Supplementary Packages

normals (raw)
corresp. (raw)

The _supp_ packages include raw normals and correspondences images, compressed losslessly.

depth (arrays)

The _depth_ packages include raw depth arrays, compressed losslessly.


The _backflow_ packages include back flow from frame F(i) to frame F(i-1).

Data Sanity Packages

Data sanity packages include per-frame sanity computed for full resolution frames.
See errata for details.


Below are the named shading and line styles. Our python utilities can easily filter sequences by style name, if you wish to only train/test on a subset. Below we also include videos of the training styles to give a sense of the styling in action, in the presence of color randomization.

Shading Styles

Line Styles

Stylit Shading Styles (Train)

Blender Shading Styles (Train)

Data Pipeline

Our data generation pipeline is available on our github page.