【Deep Learning】Review of Designing Deep Networks for Surface Normal Estimation
2016-02-02 04:40
330 查看
DesigningDeep Networks for Surface Normal Estimation
link:http://www.cs.cmu.edu/~dfouhey/deep3d/deep3d.pdf
________________________________________________
1. Summary of thePaper
By injecting insight in 3D representation, the authorsdesigned a new CNN architecture for the better demonstration of surface normalestimation. They achieve this by developing CNNs that operate both locally andglobally and moreover use fusion
method to handle these two forms of evidence.This method obtained the state-of-art performance in surface normal estimation.
2. MainContributions
1) Surprisinglyfusing global and local features and therefore better represent the surface ofobject. It’s beautifully reconciling evidence from conflicting sources.
2) Welldetecting man-made nature of indoor scenes.
3) Takingadvantage of the local constraints, they incorporate them in learning of thelocal network and as an input for the fusion network, which improve theperformance over the simple feed-forward network.
3. Positive andnegative points
Positive Points:
(i) Again,their fusion network that enables global and local constrains to be consideredtogether.
(ii) Basedon that, this method could recognize detail part of furniture in the room.
Negative Points:
(i) Cannot thinkof that.
4. How strong isthe evaluation
Very impressive.According to the Table 1., their network’s mean and median ranked lowest amongNYUv2 for per-pixel surface normal estimation.
5. Possible directionfor the future work
Myguess will be advanced fusion network that integrates the global and localinformation better. Based on this, p
link:http://www.cs.cmu.edu/~dfouhey/deep3d/deep3d.pdf
________________________________________________
1. Summary of thePaper
By injecting insight in 3D representation, the authorsdesigned a new CNN architecture for the better demonstration of surface normalestimation. They achieve this by developing CNNs that operate both locally andglobally and moreover use fusion
method to handle these two forms of evidence.This method obtained the state-of-art performance in surface normal estimation.
2. MainContributions
1) Surprisinglyfusing global and local features and therefore better represent the surface ofobject. It’s beautifully reconciling evidence from conflicting sources.
2) Welldetecting man-made nature of indoor scenes.
3) Takingadvantage of the local constraints, they incorporate them in learning of thelocal network and as an input for the fusion network, which improve theperformance over the simple feed-forward network.
3. Positive andnegative points
Positive Points:
(i) Again,their fusion network that enables global and local constrains to be consideredtogether.
(ii) Basedon that, this method could recognize detail part of furniture in the room.
Negative Points:
(i) Cannot thinkof that.
4. How strong isthe evaluation
Very impressive.According to the Table 1., their network’s mean and median ranked lowest amongNYUv2 for per-pixel surface normal estimation.
5. Possible directionfor the future work
Myguess will be advanced fusion network that integrates the global and localinformation better. Based on this, p
相关文章推荐
- 【Deep Learning】Review of Stereo Matching by Training a Convolutional Neural Network to Compare Image
- 26. Remove Duplicates from Sorted Array
- HDU 3466 (01背包)
- 【杭电】[2030]汉字统计
- JavaScript 开发进阶:理解 JavaScript 作用域和作用域链
- 一月学习总结
- 《C#入门经典(第五版)》学习笔记
- 使用 jQuery Deferred 和 Promise 创建响应式应用程序
- 【杭电】[2023]求平均成绩
- 终于搞定啦,共享一个jar包用于图片搜索
- JavaScript函数表达式
- HDU 2546
- 详解JavaScript中的函数与闭包
- HDU 2602(01背包)
- jQuery ready函数实现原理
- 前端精选文摘:BFC 神奇背后的原理
- 几个常用EL表达式的用法
- Leetcode - 285.Inorder Successor in BST
- HDU 5615
- ubuntu 安装配置 ftp