Multigrid Predictive Filter Flow for Unsupervised Learning on Videos

2 Apr 2019  ·  Shu Kong, Charless Fowlkes ·

We introduce multigrid Predictive Filter Flow (mgPFF), a framework for unsupervised learning on videos. The mgPFF takes as input a pair of frames and outputs per-pixel filters to warp one frame to the other. Compared to optical flow used for warping frames, mgPFF is more powerful in modeling sub-pixel movement and dealing with corruption (e.g., motion blur). We develop a multigrid coarse-to-fine modeling strategy that avoids the requirement of learning large filters to capture large displacement. This allows us to train an extremely compact model (4.6MB) which operates in a progressive way over multiple resolutions with shared weights. We train mgPFF on unsupervised, free-form videos and show that mgPFF is able to not only estimate long-range flow for frame reconstruction and detect video shot transitions, but also readily amendable for video object segmentation and pose tracking, where it substantially outperforms the published state-of-the-art without bells and whistles. Moreover, owing to mgPFF's nature of per-pixel filter prediction, we have the unique opportunity to visualize how each pixel is evolving during solving these tasks, thus gaining better interpretability.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Skeleton Based Action Recognition JHMDB Pose Tracking mgPFF+ft 1st PCK@0.1 58.4 # 1
PCK@0.2 78.1 # 1
PCK@0.3 85.9 # 1
PCK@0.4 89.8 # 1
PCK@0.5 92.4 # 1

Methods


No methods listed for this paper. Add relevant methods here