[Stereo_unsupervised][cvpr16]Unsupervised learning of disparity maps from stereo images
2017-12-02 11:22
405 查看
Notes of this paper which talk about unsupervised learning for stereo match
We treat correspond problem as a transformation from the left to right image.
First, we start with from the assumption that horizontal disparity is caused by horizontal shift. This could be solved by xxx lie group using Fourier theory.
In a second step, we use the general Lie group framework to allow for more general transformations.
We treat correspond problem as a transformation from the left to right image.
First, we start with from the assumption that horizontal disparity is caused by horizontal shift. This could be solved by xxx lie group using Fourier theory.
In a second step, we use the general Lie group framework to allow for more general transformations.
内容来自用户分享和网络整理，不保证内容的准确性，如有侵权内容，可联系管理员处理 
相关文章推荐
- [Paper note] Learning from Simulated and Unsupervised Images through Adversarial Training
- ZCA白化变换推导——Learning Multiple Layers of Features from Tiny Images
- 《Unsupervised Learning of Depth and Ego-Motion from Video》读书笔记
- Unsupervised Learning of Stereo Matching
- 每日论文 Learning from Simulated and Unsupervised Images through Adversarial Training
- [Stereo_cnn][cvpr16]Efficient Deep Learning for Stereo Matching(未完成)
- More 3D Graphics (rgl) for Classification with Local Logistic Regression and Kernel Density Estimates (from The Elements of Statistical Learning)（转）
- From feature descriptors to deep learning: 20 years of computer vision
- PS: Unsupervised Learning of Visual Representations Using Videos___ICCV2015
- The NOTE of learning ASP.NET [16] 关于类和对象以及封装
- What are the advantages of semi-supervised learning over supervised and unsupervised learning?
- [Stereo_cnn][cvpr16]Improved Stereo Matching with Constant Highway Networks
- ON THE EVOLUTION OF MACHINE LEARNING: FROM LINEAR MODELS TO NEURAL NETWORKS
- 立体匹配——End-to-End Learning of Geometry and Context for Deep Stereo Regression
- The Basics of 3D Printing in 2015 - from someone with 16 WHOLE HOURS' experience
- [深度学习论文笔记][CVPR 16]Deep Metric Learning via Lifted Structured Feature Embedding
- A Two-Streamed Network for Estimating Fine-Scaled Depth Maps from Single RGB Images
- [转] Download Images from Multiple Maps
- 16 Inspiring Examples of Interactive Maps in Web Design
- An Overview of the AI in Football Games from Cheating to Machine Learning..