Video Motion Stylization by 2D Rigidification

Johanna Delanoy Adrien Bousseau Aaron Hertzmann
In the 8th ACM/EG Expressive Symposium, 2019

[Paper]

Our method takes as input a video and its optical flow (a). We segment the video and optimize its pixel trajectories to produce a new video that exhibits piecewise-rigid motion (b). The resulting rigidified video can be stylized with existing algorithms (c) to produce animations where the style elements (brush strokes, paper texture) produce a strong sense of 2D motion.

Abstract

This paper introduces a video stylization method that increases the apparent rigidity of motion. Existing stylization methods often retain the 3D motion of the original video, making the result look like a 3D scene covered in paint rather than a 2D painting of a scene. In contrast, traditional hand-drawn animations often exhibit simplified in-plane motion, such as in the case of cutout animations where the animator moves pieces of paper from frame to frame. Inspired by this technique, we propose to modify a video such that its content undergoes 2D rigid transforms. To achieve this goal, our approach applies motion segmentation and optimization to best approximate the input optical flow with piecewise-rigid transforms, and re-renders the video such that its content follows the simplified motion. The output of our method is a new video and its optical flow, which can be fed to any existing video stylization algorithm.

BibTex

@InProceedings{DBH19,
  author       = "Delanoy, Johanna and Bousseau, Adrien and Hertzmann, Aaron",
  title        = "Video Motion Stylization by 2D Rigidification",
  booktitle    = "Proceedings of the 8th ACM/EG Expressive Symposium",
  month        = "may",
  year         = "2019",
  publisher    = "ACM",
  url          = "http://www-sop.inria.fr/reves/Basilic/2019/DBH19"
}