Discovering the Physical Parts of an Articulated Object Class from Multiple Videos
Citations Over TimeTop 20% of 2016 papers
Abstract
We propose a motion-based method to discover the physical parts of an articulated object class (e.g. head/torso/leg of a horse) from multiple videos. The key is to find object regions that exhibit consistent motion relative to the rest of the object, across multiple videos. We can then learn a location model for the parts and segment them accurately in the individual videos using an energy function that also enforces temporal and spatial consistency in part motion. Unlike our approach, traditional methods for motion segmentation or non-rigid structure from motion operate on one video at a time. Hence they cannot discover a part unless it displays independent motion in that particular video. We evaluate our method on a new dataset of 32 videos of tigers and horses, where we significantly outperform a recent motion segmentation method on the task of part discovery (obtaining roughly twice the accuracy).
Related Papers
- → Hybrid algorithm for estimating true motion fields(2000)20 cited
- → Effective Motion Field Description Based On Affine Models And Global Motion Information(1996)2 cited
- → <title>Motion restoration: a method for object and global motion estimation</title>(1994)1 cited
- → Parameter Estimation Of Non - Translational Motion Fields(1996)
- → Block/object-based algorithm for estimating true motion fields(2000)