Recent years have witnessed enormous progress in AI-related fields such as computer
vision, machine learning, and autonomous vehicles. As with any rapidly growing field, it …

Human activity recognition has been an important area of computer vision research since
the 1980s. Various approaches have been proposed with a great portion of them addressing …

Many applications in robotics and human-computer interaction can benefit from
understanding 3D motion of points in a dynamic environment, widely noted as scene flow …

Recent work has shown that optical flow estimation can be formulated as a supervised
learning task and can be successfully solved with convolutional networks. Training of the so …

This paper proposes a novel model and dataset for 3D scene flow estimation with an
application to autonomous driving. Taking advantage of the fact that outdoor scenes often …

Occlusions play an important role in optical flow and disparity estimation, since matching
costs are not available in occluded areas and occlusions indicate motion boundaries …

The problem of determining whether an object is in motion, irrespective of camera motion, is
far from being solved. We address this challenging task by learning motion patterns in …

Scene flow estimation is a long-standing problem in computer vision, where the goal is to
find the 3D motion of a scene from its consecutive observations. Recently, there have been …

Scene flow characterizes the 3D motion between two LiDAR scans captured by an
autonomous vehicle at nearby timesteps. Prevalent methods consider scene flow as point …

Object tracking and 3D reconstruction are often performed together, with tracking used as
input for reconstruction. However, the obtained reconstructions also provide useful …