LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation
Abstract flownet效果好，但是需要160M的参数。创新点：1.使得前向传播预测光流更为效率通过在每一个金字塔层添加一个串联网络。2.添加一个novel flow regularization layer来改善异常值和模糊边界的情况，这个层是通过使用feature-driven local convolution来实现的。3.我们的网络拥有一个有效的金字塔特征提取结构，并采用fea
相关文章
- 1. Optical Flow 发展历程 (1)
- 2. PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes—2017（笔记）
- 3. FlowNet: Learning Optical Flow with Convolutional Networks
- 4. 论文解读1-LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation
- 5. Tensorflow - Implement for a Convolutional Neural Network on MNIST.
- 6. A Cascaded Convolutional Neural Network for Single Image Dehazing
- 7. 《A Convolutional Neural Network Cascade for Face Detection》
- 8. A mixed-scale dense convolutional neural network for image analysis
- 9. Deep Alignment Network: A convolutional neural network for robust face alignment
- 10. FlowNet 2.0 Evolution of Optical Flow Estimation with Deep Networks
- 更多相关文章...
- • XSL-FO flow 对象 - XSL-FO 教程
- • Scala for循环 - Scala教程
- • Flink 数据传输及反压详解
- • YAML 入门教程
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
最新文章
欢迎关注本站公众号,获取更多信息
相关文章
- 1. Optical Flow 发展历程 (1)
- 2. PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes—2017（笔记）
- 3. FlowNet: Learning Optical Flow with Convolutional Networks
- 4. 论文解读1-LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation
- 5. Tensorflow - Implement for a Convolutional Neural Network on MNIST.
- 6. A Cascaded Convolutional Neural Network for Single Image Dehazing
- 7. 《A Convolutional Neural Network Cascade for Face Detection》
- 8. A mixed-scale dense convolutional neural network for image analysis
- 9. Deep Alignment Network: A convolutional neural network for robust face alignment
- 10. FlowNet 2.0 Evolution of Optical Flow Estimation with Deep Networks