SegFlow: Joint Learning for Video Object Segmentation & Optical Flow
ICCV 2017 | We propose an end-to-end trainable network, SegFlow, for simultaneously predicting pixel-wise object segmentation and optical flow in videos. The proposed SegFlow has two branches where useful information of object segmentation and optical flow is propagated bidirectionally in a unified framework. The unified framework can be trained iteratively offline to learn a generic notion, or it can be fine-tuned online for specific objects.
Collaborators: Jingchun Cheng, Yi-Hsuan Tsai, Shengjin Wang, Ming-Hsuan Yang