Understanding Image Motion with Group Representations
Motion perception is a key component of computer vision. It is critical to problems such as optical flow and visual odometry, where a sequence of images are used to calculate either the pixel level (local) motion or the motion of the entire scene (global). The smooth image transformation caused by camera motion is a subspace of all position image transformations. Here, we are interested in realistic transformation caused by motion, therefore unrealistic motion caused by say, face swapping, are not considered.
Supervised learning of 3D motion is challenging since explicit motion labels are no trivial to obtain. The proposed learning method does not need label data. Instead, the method constraints learning by using the properties of motion space. The paper presents a general model of visual motion, and how the motion space properties of associativity and can be used to constrain the learning of a deep neural network. The results show evidence that the learned model captions motion in both 2D and 3D settings.
The most common global representations of motion are from structure from motion (SfM) and simultaneous localization and mapping (SLAM), which represents poses in special Euclidean group (SE(3)) to represent a sequence of motions. However, these cannot be used to represent non-rigid or independent motions. Other approaches to representing motion is spatio-temporal features (STFs).