202 citations · 209 across the 8 of their papers we have counts for
9 papers
SemARFlow: Injecting Semantics into Unsupervised Optical Flow Estimation for Autonomous Driving
Shuai Yuan, Shuzhi Yu, Hannah Kim +1
Unsupervised optical flow estimation is especially hard near occlusions and motion boundaries and in low-texture regions. We show that additional information such as semantics and…
Unsupervised Flow Refinement near Motion Boundaries
Shuzhi Yu, Hannah Halin Kim, Shuai Yuan +1
Unsupervised optical flow estimators based on deep learning have attracted increasing attention due to the cost and difficulty of annotating for ground truth. Although performance…
Cross-Attention Transformer for Video Interpolation
Hannah Halin Kim, Shuzhi Yu, Shuai Yuan +1
We propose TAIN (Transformers and Attention for video INterpolation), a residual neural network for video interpolation, which aims to interpolate an intermediate frame given two c…
Optical Flow Training under Limited Label Budget via Active Learning
Shuai Yuan, Xian Sun, Hannah Kim +2
Supervised training of optical flow predictors generally yields better accuracy than unsupervised training. However, the improved performance comes at an often high annotation cost…
Joint Detection of Motion Boundaries and Occlusions
Hannah Halin Kim, Shuzhi Yu, Carlo Tomasi
We propose MONet, a convolutional neural network that jointly detects motion boundaries (MBs) and occlusion regions (Occs) in video both forward and backward in time. Detection is…
Identity Connections in Residual Nets Improve Noise Stability
Shuzhi Yu, Carlo Tomasi
Residual Neural Networks (ResNets) achieve state-of-the-art performance in many computer vision problems. Compared to plain networks without residual connections (PlnNets), ResNets…