Deployed 71a9a2b with MkDocs version: 1.4.2

changelog/index.html

@@ -939,6 +939,7 @@ <h1 id="changelog">Changelog<a class="headerlink" href="#changelog" title="Perma
 <div class="heti-skip">
 <h2 id="2024">2024 年<a class="headerlink" href="#2024" title="Permanent link">¶</a></h2>
 <ul>
+<li><span style="font-family: var(--md-code-font-family)">01-15 <a href="https://github.com/ZJU-Turing/TuringCourses/commit/71a9a2b65b7e91986578a2d0dfef5338355cbbc0">71a9a2b</a> </span>docs: 更新<a href="https://zju-turing.github.io/TuringCourses/major_mandatory/computer_vision/">计算机视觉导论</a>课程内容 (<a href="https://github.com/ZJU-Turing/TuringCourses/pull/116">#116</a>)</li>
 <li><span style="font-family: var(--md-code-font-family)">01-14 <a href="https://github.com/ZJU-Turing/TuringCourses/commit/3005ade9f3e9b89c6ef8f7d9615acce39f7fa447">3005ade</a> </span>docs: 添加数学分析（甲）I（H）2023秋冬期末回忆卷<ul>
 <li>🔗 <a href="https://zju-turing.github.io/TuringCourses/math_phys/math_analysis1/">数学分析（甲）Ⅰ（H）</a> </li>
 </ul>

major_mandatory/computer_vision/index.html

@@ -974,7 +974,7 @@
 <svg viewbox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><path d="M20.71 7.04c.39-.39.39-1.04 0-1.41l-2.34-2.34c-.37-.39-1.02-.39-1.41 0l-1.84 1.83 3.75 3.75M3 17.25V21h3.75L17.81 9.93l-3.75-3.75L3 17.25Z"></path></svg>
 </a>
 <div class="admonition warning">
-<p class="admonition-title">1675825592</p>
+<p class="admonition-title">1705309190</p>
 </div>
 <h1 id="_1">计算机视觉导论<a class="headerlink" href="#_1" title="Permanent link"><span><span class="heti-spacing"> </span>¶</span></a></h1>
 <div class="badges">
@@ -1000,16 +1000,26 @@ <h2 id="_2">课程学习内容<a class="headerlink" href="#_2" title="Permanent
 </ol>
 <p>除此主线内容之外，在最开始会有一个导论和对线性代数的简单回顾，在<span class="heti-skip"><span class="heti-spacing"> </span>2<span class="heti-spacing"> </span></span>和<span class="heti-skip"><span class="heti-spacing"> </span>3<span class="heti-spacing"> </span></span>之间会有一个对优化方法的介绍，在<span class="heti-skip"><span class="heti-spacing"> </span>6<span class="heti-spacing"> </span></span>和<span class="heti-skip"><span class="heti-spacing"> </span>7<span class="heti-spacing"> </span></span>之间会有一个对深度学习的介绍。</p>
 <p>这门课的大作业是三维重建<span class="heti-skip"><span class="heti-spacing"> </span>+<span class="heti-spacing"> </span></span>位姿估计。一般使用<a href="https://github.com/cvg/Hierarchical-Localization"><span class="heti-skip"><span class="heti-spacing"> </span>Hierachical Localization<span class="heti-spacing"> </span></span></a>就可以得到一个比较好的结果，稍微微调一下参数做一下预处理也是可以的。虽然是打榜的形式，但是事实上按照笔者的体验分差并不明显，最后会有一个课堂展示<span class="heti-skip"><span class="heti-spacing"> </span>+<span class="heti-spacing"> </span></span>验收。</p>
+<p>但是从<span class="heti-skip"><span class="heti-spacing"> </span>23-24<span class="heti-spacing"> </span></span>秋冬开始，由于大作业打榜的形式造成大家最后都用差不多的方法，而且<span class="heti-skip"><span class="heti-spacing"> </span>leaderboard<span class="heti-spacing"> </span></span>的形式太卷了，因此大作业改成了五选一的形式。今年的五个题目分别是：</p>
+<ul>
+<li>光心不一致时的全景图拼接</li>
+<li>重建校园某区域，基于图像对自身做定位</li>
+<li>从多视角视频还原车辆、行人轨迹</li>
+<li>基于多视角图片重建小动物<span class="heti-skip"><span class="heti-spacing"> </span>/<span class="heti-spacing"> </span></span>人</li>
+<li>参考一段网络舞蹈视频，合成自己跳舞的视频</li>
+</ul>
+<p>其中每个任务都分为基础解决方案和额外提升方案。大作业整体的工作量是比较大的，但是课程提供了<span class="heti-skip"><span class="heti-spacing"> </span>GPU<span class="heti-spacing"> </span></span>资源，同时如果遇到困难都可以问助教，助教都是周老师的博士生，水平很高而且人也很好。</p>
 <p>课程有实验课，实验普遍比较简单，可以不去上课。当然，有一次课会讲怎么使用<span><span class="heti-spacing"> </span>COLMAP</span> ，那一次课前周老师也会提醒，也建议稍微去听一下，虽然只看文档也能折腾明白。<span>6<span class="heti-spacing"> </span></span>次实验的内容分别是：</p>
 <ol>
 <li><span>matplotlib, OpenCV<span class="heti-spacing"> </span></span>和<span class="heti-skip"><span class="heti-spacing"> </span>Open3d<span class="heti-spacing"> </span></span>的基本使用方式；</li>
 <li>高斯滤波、中值滤波、双边滤波和透视投影的实现；</li>
 <li>使用<span class="heti-skip"><span class="heti-spacing"> </span>Gauss-Newton<span class="heti-spacing"> </span></span>法求解优化问题；</li>
 <li>图片匹配和图片拼接：<span>Harris<span class="heti-spacing"> </span></span>角点检测、<span>SIFT<span class="heti-spacing"> </span></span>和<span class="heti-skip"><span class="heti-spacing"> </span>RANSAC<span class="heti-spacing"> </span></span>来计算单映变换；</li>
 <li>使用<span class="heti-skip"><span class="heti-spacing"> </span>COLMAP<span class="heti-spacing"> </span></span>完成<span class="heti-skip"><span class="heti-spacing"> </span>SfM<span class="heti-spacing"> </span></span>和（可选的）MVS；</li>
-<li>使用<span class="heti-skip"><span class="heti-spacing"> </span>mmdetection<span class="heti-spacing"> </span></span>完成目标检测。</li>
+<li>使用<span class="heti-skip"><span class="heti-spacing"> </span>mmdetection<span class="heti-spacing"> </span></span>完成目标检测<span class="heti-skip"><span class="heti-spacing"> </span>,<span class="heti-spacing"> </span></span>写一个<span class="heti-skip"><span class="heti-spacing"> </span>CNN<span class="heti-spacing"> </span></span>完成图像分类。</li>
 </ol>
 <p>期末考试不考后面<span class="heti-skip"><span class="heti-spacing"> </span>7 8 9 10<span class="heti-spacing"> </span></span>节的内容，当然，周老师会在复习课上讲明考试范围，这个范围仅供参考，复习课讲的更加细致。<span>20<span class="heti-spacing"> </span></span>级的考试大题印象中有一道图像拼接和一道三维重建，考的都比较基础，给分普遍似乎也不错，不用过于担心。</p>
+<p><span>23-24<span class="heti-spacing"> </span></span>秋冬课程所有的内容都有涉及，考察的内容不难但是覆盖面很大，有很多内容比较细节。分为<span class="heti-skip"><span class="heti-spacing"> </span>30<span class="heti-spacing"> </span></span>分的不定项选择题，<span>20<span class="heti-spacing"> </span></span>分的判断题，<span>20<span class="heti-spacing"> </span></span>分的填空题，<span>30<span class="heti-spacing"> </span></span>分的大题。</p>
 <h3 id="_3">先修要求<a class="headerlink" href="#_3" title="Permanent link"><span><span class="heti-spacing"> </span>¶</span></a></h3>
 <p>可以没有。线性代数会用就足够了，也不会在考试要求计算；前几节内容在图像信息处理课程中会讲，但是没上过也没有风险；机器学习当然上过最好，但是周老师会把所有用到的内容讲清楚，甚至可能比隔壁赵洲老师还清楚，所以没上过也无伤大雅；在渲染的讲解中也会涉及计算机图形学的内容，同样会有充分的介绍；除此以外，还有一门计算摄影的课程，也是周老师开的，笔者没有上过不知晓详情。</p>
 <p>总而言之，课程内容自洽，但与很多课程重合。如果有兴趣自然可以往某个方向多多拓展，但如果只是通过考试那么完全没有必要担心什么基础知识不足。</p>
@@ -1019,12 +1029,13 @@ <h2 id="_4">任课教师<a class="headerlink" href="#_4" title="Permanent link">
 <h2 id="_5">课程教材<a class="headerlink" href="#_5" title="Permanent link"><span><span class="heti-spacing"> </span>¶</span></a></h2>
 <p>如果没有改的话，推荐的参考书目应当还是<a href="http://szeliski.org/Book/"><span class="heti-skip"><span class="heti-spacing"> </span>Szeliski<span class="heti-spacing"> </span></span>的 <em>Computer Vision</em></a>，填写邮箱可以免费下载。这本书的内容比课程内容多且更加复杂，如果只是想通过考试，听课也就够了，对于计算机视觉感兴趣的同学可以仔细阅读。</p>
 <h2 id="_6">分数构成<a class="headerlink" href="#_6" title="Permanent link"><span><span class="heti-spacing"> </span>¶</span></a></h2>
-<p>平时作业<span class="heti-skip"><span class="heti-spacing"> </span>30% +<span class="heti-spacing"> </span></span>大作业<span class="heti-skip"><span class="heti-spacing"> </span>40% +<span class="heti-spacing"> </span></span>期末考试<span><span class="heti-spacing"> </span>30%</span>。</p>
+<p>平时作业<span class="heti-skip"><span class="heti-spacing"> </span>30% +<span class="heti-spacing"> </span></span>大作业<span class="heti-skip"><span class="heti-spacing"> </span>30% +<span class="heti-spacing"> </span></span>期末考试<span><span class="heti-spacing"> </span>40%</span>。</p>
 <h2 id="_7">推荐书目<a class="headerlink" href="#_7" title="Permanent link"><span><span class="heti-spacing"> </span>¶</span></a></h2>
 <p>关于三维重建，因为这是这门课的一个重点，推荐<a href="https://www.cambridge.org/core/books/multiple-view-geometry-in-computer-vision/0B6F289C78B2B23F596CAA76D3D43F7A"><span class="heti-skip"><span class="heti-spacing"> </span>Richard Hartley<span class="heti-spacing"> </span></span>和<span class="heti-skip"><span class="heti-spacing"> </span>Andrew Zisserman<span class="heti-spacing"> </span></span>的 <em>Multiple View Geometry in Computer Vision</em></a> ，这本书中的推导可能比课上的更加简单明快，感兴趣的同学也可以翻阅。</p>
 <h2 id="_8">参考笔记<a class="headerlink" href="#_8" title="Permanent link"><span><span class="heti-spacing"> </span>¶</span></a></h2>
 <ul>
 <li><a href="https://frightenedfoxcn.github.io/notes/qnotes/computer_vision/"><span>lhj<span class="heti-spacing"> </span></span>的笔记</a></li>
+<li><a href="https://lhxcs.github.io/note/AI/cv/icv/"><span>lhx<span class="heti-spacing"> </span></span>的笔记</a></li>
 </ul>
 <hr/>
 <style>
@@ -1055,7 +1066,7 @@ <h2 id="_8">参考笔记<a class="headerlink" href="#_8" title="Permanent link">
 }
 </style>
 <div id="footer-wrapper">
-<p><span class="twemoji"><svg viewbox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><path d="M21 13.1c-.1 0-.3.1-.4.2l-1 1 2.1 2.1 1-1c.2-.2.2-.6 0-.8l-1.3-1.3c-.1-.1-.2-.2-.4-.2m-1.9 1.8-6.1 6V23h2.1l6.1-6.1-2.1-2M12.5 7v5.2l4 2.4-1 1L11 13V7h1.5M11 21.9c-5.1-.5-9-4.8-9-9.9C2 6.5 6.5 2 12 2c5.3 0 9.6 4.1 10 9.3-.3-.1-.6-.2-1-.2s-.7.1-1 .2C19.6 7.2 16.2 4 12 4c-4.4 0-8 3.6-8 8 0 4.1 3.1 7.5 7.1 7.9l-.1.2v1.8Z"></path></svg></span> 2023-02-08  <span class="twemoji"><svg viewbox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><path d="M12 .297c-6.63 0-12 5.373-12 12 0 5.303 3.438 9.8 8.205 11.385.6.113.82-.258.82-.577 0-.285-.01-1.04-.015-2.04-3.338.724-4.042-1.61-4.042-1.61C4.422 18.07 3.633 17.7 3.633 17.7c-1.087-.744.084-.729.084-.729 1.205.084 1.838 1.236 1.838 1.236 1.07 1.835 2.809 1.305 3.495.998.108-.776.417-1.305.76-1.605-2.665-.3-5.466-1.332-5.466-5.93 0-1.31.465-2.38 1.235-3.22-.135-.303-.54-1.523.105-3.176 0 0 1.005-.322 3.3 1.23.96-.267 1.98-.399 3-.405 1.02.006 2.04.138 3 .405 2.28-1.552 3.285-1.23 3.285-1.23.645 1.653.24 2.873.12 3.176.765.84 1.23 1.91 1.23 3.22 0 4.61-2.805 5.625-5.475 5.92.42.36.81 1.096.81 2.22 0 1.606-.015 2.896-.015 3.286 0 .315.21.69.825.57C20.565 22.092 24 17.592 24 12.297c0-6.627-5.373-12-12-12"></path></svg></span> Contributors <span class="contributors"><a href="https://github.com/TonyCrane" target="_blank" title="TonyCrane"><img alt="TonyCrane" src="https://avatars.githubusercontent.com/u/44120331"/></a><a href="https://github.com/FrightenedFoxCN" target="_blank" title="FrightenedFoxCN"><img alt="FrightenedFoxCN" src="https://avatars.githubusercontent.com/u/71172070"/></a></span></p>
+<p><span class="twemoji"><svg viewbox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><path d="M21 13.1c-.1 0-.3.1-.4.2l-1 1 2.1 2.1 1-1c.2-.2.2-.6 0-.8l-1.3-1.3c-.1-.1-.2-.2-.4-.2m-1.9 1.8-6.1 6V23h2.1l6.1-6.1-2.1-2M12.5 7v5.2l4 2.4-1 1L11 13V7h1.5M11 21.9c-5.1-.5-9-4.8-9-9.9C2 6.5 6.5 2 12 2c5.3 0 9.6 4.1 10 9.3-.3-.1-.6-.2-1-.2s-.7.1-1 .2C19.6 7.2 16.2 4 12 4c-4.4 0-8 3.6-8 8 0 4.1 3.1 7.5 7.1 7.9l-.1.2v1.8Z"></path></svg></span> 2024-01-15  <span class="twemoji"><svg viewbox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><path d="M12 .297c-6.63 0-12 5.373-12 12 0 5.303 3.438 9.8 8.205 11.385.6.113.82-.258.82-.577 0-.285-.01-1.04-.015-2.04-3.338.724-4.042-1.61-4.042-1.61C4.422 18.07 3.633 17.7 3.633 17.7c-1.087-.744.084-.729.084-.729 1.205.084 1.838 1.236 1.838 1.236 1.07 1.835 2.809 1.305 3.495.998.108-.776.417-1.305.76-1.605-2.665-.3-5.466-1.332-5.466-5.93 0-1.31.465-2.38 1.235-3.22-.135-.303-.54-1.523.105-3.176 0 0 1.005-.322 3.3 1.23.96-.267 1.98-.399 3-.405 1.02.006 2.04.138 3 .405 2.28-1.552 3.285-1.23 3.285-1.23.645 1.653.24 2.873.12 3.176.765.84 1.23 1.91 1.23 3.22 0 4.61-2.805 5.625-5.475 5.92.42.36.81 1.096.81 2.22 0 1.606-.015 2.896-.015 3.286 0 .315.21.69.825.57C20.565 22.092 24 17.592 24 12.297c0-6.627-5.373-12-12-12"></path></svg></span> Contributors <span class="contributors"><a href="https://github.com/TonyCrane" target="_blank" title="TonyCrane"><img alt="TonyCrane" src="https://avatars.githubusercontent.com/u/44120331"/></a><a href="https://github.com/FrightenedFoxCN" target="_blank" title="FrightenedFoxCN"><img alt="FrightenedFoxCN" src="https://avatars.githubusercontent.com/u/71172070"/></a><a href="https://github.com/lhxcs" target="_blank" title="lhxcs"><img alt="lhxcs" src="https://avatars.githubusercontent.com/u/133565095"/></a></span></p>
 </div>
 <style>
 .md-content .admonition:first-of-type {