Stereo vision is a flourishing field, attracting the attention of many researchers. Recently,
leveraging on the development of deep learning, stereo matching algorithms have achieved …

Most online multi-object trackers perform object detection stand-alone in a neural net without
any input from tracking. In this paper, we present a new online joint detection and tracking …

Occlusions pose a significant challenge to optical flow algorithms that rely on local
evidences. We consider an occluded point to be one that is imaged in the first frame but not …

Abstract We introduce Recurrent All-Pairs Field Transforms (RAFT), a new deep network
architecture for optical flow. RAFT extracts per-pixel features, builds multi-scale 4D …

Establishing correspondence between images or scenes is a significant challenge in
computer vision, especially given occlusions, viewpoint changes, and varying object …

Optical flow estimation aims to find the 2D motion field by identifying corresponding pixels
between two images. Despite the tremendous progress of deep learning-based optical flow …

Current state-of-the-art trackers rely only on a target appearance model in order to localize
the object in each frame. Such approaches are however prone to fail in case of eg fast …

Methods for video motion prediction either estimate jointly the instantaneous motion of all
points in a given video frame using optical flow or independently track the motion of …

Many video enhancement algorithms rely on optical flow to register frames in a video
sequence. Precise flow estimation is however intractable; and optical flow itself is often a …

Video interpolation increases the temporal resolution of a video sequence by synthesizing
intermediate frames between two consecutive frames. We propose a novel deep-learning …