mirror of
https://github.com/PKUFlyingPig/cs-self-learning.git
synced 2026-06-23 01:47:13 +08:00
[COURSE] Add 3D Reconstruction
This commit is contained in:
parent
c14dde8d9e
commit
46fc0b876e
2 changed files with 33 additions and 0 deletions
30
docs/计算机视觉/3DReconstruction.md
Normal file
30
docs/计算机视觉/3DReconstruction.md
Normal file
|
|
@ -0,0 +1,30 @@
|
|||
# 课程名称 计算机视觉三维重建
|
||||
|
||||
## 课程简介
|
||||
|
||||
- 所属大学:北京邮电大学
|
||||
|
||||
- 先修要求:无
|
||||
|
||||
- 编程语言:无
|
||||
|
||||
- 课程难度:🌟🌟
|
||||
|
||||
- 预计学时:14
|
||||
|
||||
<!-- 用一两段话介绍这门课程,内容包括但不限于:
|
||||
(1)课程覆盖的知识点范围
|
||||
(2)与同类课程相比它的优势与特点
|
||||
(3)学习这门课程的体验与感受
|
||||
(4)自学这门课的注意点(踩过的坑、难度预警等等)
|
||||
(5)... ...
|
||||
-->
|
||||
|
||||
本门课程是介绍与讨论计算机视觉三维重建的基础课程,课程中详细讲述了如何从图像构建三维模型的过程。相比于同类课程,知识点更加详细,公式推导更加完整,对于入门SLAM与3D Reconstruction的初学者极其友好,网上博客与资料等自学的方式多出现错误(本人亲身经历),因此相比之下,此课程是极其优秀的课程。
|
||||
|
||||
**本门课程没有实践过程,完全属于理论课,如果对推导过程有兴趣的同学,可以尝试用代码复现其算法过程。**
|
||||
|
||||
## 课程资源
|
||||
|
||||
- 课程网站:[2022B站最好最全的【三维重建】课程!!!北邮教授竟然把三维重建讲的如此通俗易懂,学不会UPZHIJIE 退网下架!!!-人工智能/计算机视觉/三维重建_哔哩哔哩_bilibili](https://www.bilibili.com/video/BV1DP41157dB/?spm_id_from=333.337.search-card.all.click&vd_source=416d3ea01e1c64f6ca346be77e374549)
|
||||
- 课程视频:[2022B站最好最全的【三维重建】课程!!!北邮教授竟然把三维重建讲的如此通俗易懂,学不会UPZHIJIE 退网下架!!!-人工智能/计算机视觉/三维重建_哔哩哔哩_bilibili](https://www.bilibili.com/video/BV1DP41157dB/?spm_id_from=333.337.search-card.all.click&vd_source=416d3ea01e1c64f6ca346be77e374549)
|
||||
|
|
@ -105,6 +105,7 @@ plugins:
|
|||
机器学习系统: Machine Learning Systems
|
||||
深度学习: Deep Learning
|
||||
机器学习进阶: Advanced Machine Learning
|
||||
计算机视觉: Computer Vision
|
||||
后记: Postscript
|
||||
- search:
|
||||
lang:
|
||||
|
|
@ -252,4 +253,6 @@ nav:
|
|||
- "Columbia STAT 8201: Deep Generative Models": "机器学习进阶/STAT8201.md"
|
||||
- "U Toronto STA 4273 Winter 2021: Minimizing Expectations": "机器学习进阶/STA4273.md"
|
||||
- "Stanford STATS214 / CS229M: Machine Learning Theory": "机器学习进阶/CS229M.md"
|
||||
- 计算机视觉:
|
||||
- "计算机视觉之三维重建": "计算机视觉/3DReconstruction.md"
|
||||
- 后记: "后记.md"
|
||||
|
|
|
|||
Loading…
Reference in a new issue