no code implementations • 27 May 2019 • Shuzhi Yu, Carlo Tomasi
Residual Neural Networks (ResNets) achieve state-of-the-art performance in many computer vision problems.
1 code implementation • 1 Nov 2021 • Hannah Halin Kim, Shuzhi Yu, Carlo Tomasi
Since appearance mismatches between frames often signal vicinity to MBs or Occs, we construct a cost block that for each feature in one frame records the lowest discrepancy with matching features in a search range.
1 code implementation • 9 Mar 2022 • Shuai Yuan, Xian Sun, Hannah Kim, Shuzhi Yu, Carlo Tomasi
Supervised training of optical flow predictors generally yields better accuracy than unsupervised training.
no code implementations • 11 May 2022 • Shuzhi Yu, Guanhang Wu, Chunhui Gu, Mohammed E. Fathy
However, their success depends on the availability of videos that are fully annotated with tracking data, which is expensive and hard to obtain.
1 code implementation • 8 Jul 2022 • Hannah Halin Kim, Shuzhi Yu, Shuai Yuan, Carlo Tomasi
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 consecutive image frames around it.
no code implementations • 3 Aug 2022 • Shuzhi Yu, Hannah Halin Kim, Shuai Yuan, Carlo Tomasi
Unsupervised optical flow estimators based on deep learning have attracted increasing attention due to the cost and difficulty of annotating for ground truth.
1 code implementation • ICCV 2023 • Shuai Yuan, Shuzhi Yu, Hannah Kim, Carlo Tomasi
We show that additional information such as semantics and domain knowledge can help better constrain this problem.