Review of stereo matching algorithms based on deep learning
K Zhou, X Meng, B Cheng - Computational intelligence and …, 2020 - Wiley Online Library
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 …
leveraging on the development of deep learning, stereo matching algorithms have achieved …
Track to detect and segment: An online multi-object tracker
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 …
any input from tracking. In this paper, we present a new online joint detection and tracking …
Learning to estimate hidden motions with global motion aggregation
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 …
evidences. We consider an occluded point to be one that is imaged in the first frame but not …
Raft: Recurrent all-pairs field transforms for optical flow
Z Teed, J Deng - Computer Vision–ECCV 2020: 16th European …, 2020 - Springer
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 …
architecture for optical flow. RAFT extracts per-pixel features, builds multi-scale 4D …
Siamese masked autoencoders
Establishing correspondence between images or scenes is a significant challenge in
computer vision, especially given occlusions, viewpoint changes, and varying object …
computer vision, especially given occlusions, viewpoint changes, and varying object …
Craft: Cross-attentional flow transformer for robust optical flow
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 …
between two images. Despite the tremendous progress of deep learning-based optical flow …
Know your surroundings: Exploiting scene information for object tracking
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 …
the object in each frame. Such approaches are however prone to fail in case of eg fast …
Cotracker: It is better to track together
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 …
points in a given video frame using optical flow or independently track the motion of …
Video enhancement with task-oriented flow
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 …
sequence. Precise flow estimation is however intractable; and optical flow itself is often a …
Bmbc: Bilateral motion estimation with bilateral cost volume for video interpolation
Video interpolation increases the temporal resolution of a video sequence by synthesizing
intermediate frames between two consecutive frames. We propose a novel deep-learning …
intermediate frames between two consecutive frames. We propose a novel deep-learning …