Blog(1)
Optical flow targets at estimating per-pixel correspondences between a source image and a target image, in the form of a 2D displacement field.
Research Areas(0)
Publications(6)
What's in the Flow? Exploiting Temporal Motion Cues for Unsupervised Generic Event Boundary Detection
AuthorSourabh Vasant Gothe, Vibhav Agarwal, Sourav Ghosh, Jayesh Rajkumar Vachhani, Pranay Kashyap, Barath Raj Kandur Raja
PublishedIEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Date2024-01-03
FlowFormer: A Transformer Architecture for Optical Flow
AuthorChao Zhang, Qiang Wang
PublishedEuropean Conference on Computer Vision (ECCV)
Date2022-12-01
Enhanced Bi-directional Motion Estimation for Video Frame Interpolation
AuthorXin Jin (xin.jin) Longhai Wu (longhai.wu) Guotao Shen (guotao.shen) Youxin Chen (yx113.chen) Jie Chen (ada.chen) Jay Koo (j.goo) CHEUL-HEE HAHM (chhahm)
Date2022-08-17
News(2)
Video frame interpolation aims to increase the frame rate of videos, by synthesizing non-existent intermediate frames between original successive frames. With recent advances in optical flow, motion-based interpolation has developed into a promising framework.
Others(0)