We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Trainable TV-L1 model as recurrent nets for low-level vision.
- Authors
Fang, Yuqiang; Ma, Zhihao; Zheng, Hao; Ji, Wanting
- Abstract
TV- L 1 is a classical diffusion–reaction model for low-level vision tasks, which can be solved by a duality-based iterative algorithm. Considering the recent success of end-to-end learned representations, we propose a TV-LSTM network to unfold the duality-based iterations of TV- L 1 into long short-term memory (LSTM) cells. In particular, we formulate the iterations as customized layers of a LSTM neural network. Then, the proposed end-to-end trainable TV-LSTMs can be naturally connected with various task-specific networks, e.g., optical flow, image decomposition and event-based optical flow estimation. Extensive experiments on optical flow estimation and structure + texture decomposition have demonstrated the effectiveness and efficiency of the proposed method.
- Subjects
OPTICAL flow; ALGORITHMS; PROGRAMMED cell death 1 receptors
- Publication
Neural Computing & Applications, 2020, Vol 32, Issue 18, p14603
- ISSN
0941-0643
- Publication type
Article
- DOI
10.1007/s00521-020-05146-5