From Tv-L-1 To Gated Recurrent Nets

2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)(2019)

引用 1|浏览78
暂无评分
摘要
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 into long short-term memory (LSTM) cells. To provide a trainable network, we relax the difference operators in the gate and cell update of TV-LSTM to trainable parameters. Then, the proposed end-to-end trainable TV-LSTMs can be naturally connected with various task-specific networks, e.g., optical flow estimation and image decomposition. Extensive experiments on optical flow estimation and structure + texture decomposition have demonstrated the effectiveness and efficiency of the proposed method.
更多
查看译文
关键词
total variation, optical flow, recurrent neural network, image decomposition
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要