Motion Segmentation is an essential task in many applications in Computer Vision and Robotics, such as surveillance, action recognition and scene understanding. The classic way to state the problem is the following: given a set of feature points that are tracked through a sequence of images, the goal is to cluster those trajectories according to the different motions they belong to. It is assumed that the scene contains multiple objects that are moving rigidly and independently in 3D-space.
We address the unsupervised learning of several interconnected problems in low-level vision: single view depth prediction, camera motion estimation, optical flow, and segmentation of a video into the static scene and moving regions.
Ranked #21 on
Monocular Depth Estimation
on KITTI Eigen split
MONOCULAR DEPTH ESTIMATION MOTION ESTIMATION MOTION SEGMENTATION OPTICAL FLOW ESTIMATION
In this work, we propose a novel deep neural network named $FlowNet3D$ that learns scene flow from point clouds in an end-to-end fashion.
In this paper, we propose and study an algorithm, called Sparse Subspace Clustering (SSC), to cluster data points that lie in a union of low-dimensional subspaces.
Ranked #4 on
Motion Segmentation
on Hopkins155
In this paper, we propose UnOS, an unified system for unsupervised optical flow and stereo depth estimation using convolutional neural network (CNN) by taking advantages of their inherent geometrical consistency based on the rigid-scene assumption.
MOTION SEGMENTATION OPTICAL FLOW ESTIMATION STEREO DEPTH ESTIMATION VISUAL ODOMETRY
Whole understanding of the surroundings is paramount to autonomous systems.
KNOWLEDGE DISTILLATION MONOCULAR DEPTH ESTIMATION MOTION SEGMENTATION OPTICAL FLOW ESTIMATION SCENE UNDERSTANDING
Geometric motion segmentation algorithms, however, generalize to novel scenes, but have yet to achieve comparable performance to appearance-based ones, due to noisy motion estimations and degenerate motion configurations.
The Progressive-X algorithm, Prog-X in short, is proposed for geometric multi-model fitting.
Our model jointly estimates (i) the segmentation of the scene into an unknown but finite number of objects, (ii) the motion trajectories of these objects and (iii) the object scene flow.
The move replaces a set of labels with the corresponding density mode in the model parameter domain, thus achieving fast and robust optimization.
To handle the nonrigid background like a sea, we also propose a robust fusion mechanism between motion and appearance-based features.
MOTION SEGMENTATION OPTICAL FLOW ESTIMATION UNSUPERVISED VIDEO OBJECT SEGMENTATION