2017 IEEE International Conference on Computer Vision

Temporal Superpixels Based on
Proximity-Weighted Patch Matching

Se-Ho Lee
Korea University

Won-Dong Jang
Korea University

Chang-Su Kim
Korea University


A temporal superpixel algorithm based on proximity-weighted patch matching (TS-PPM) is proposed in this work. We develop the proximity-weighted patch matching (PPM), which estimates the motion vector of a superpixel robustly, by considering the patch matching distances of neighboring superpixels as well as the target superpixel. In each frame, we initialize superpixels by transferring the superpixel labels of the previous frame using PPM motion vectors. Then, we update the superpixel labels of boundary pixels, based on a cost function, composed of color, spatial, contour, and temporal consistency terms. Finally, we execute superpixel splitting, merging, and relabeling to regularize superpixel sizes and reduce incorrect labels. Experiments show that the proposed algorithm outperforms the state-of-the-art conventional algorithms significantly.

Supplementary Video



  • Se-Ho Lee, Won-Dong Jang, and Chang-Su Kim, "Temporal superpixels based on proximity-weighted patch matching," In Proc. IEEE International Conference on Computer Vision (ICCV), Venice, Italy, pp. 3610-3618, Oct. 2017.

  • Download

  • Source code: ICCV17_TS-PPM_SHLee.zip