TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Unsupervised learning of probably symmetric deformable 3D objects from images

181 点作者 jotaf大约 5 年前

10 条评论

jcims大约 5 年前
Stuff like this can obviously be used to make things like deepfakes &#x27;better&#x27;. But i think it might be cool for creating virtual meeting rooms, where you can take a webcam shot of a persons face, normalize the skin tones for lighting, map to a 3d surface, then relight it for the virtual room.<p>When you can rig the meshes to drive each other you could wear &#x27;masks&#x27; of other peoples faces (or critters).
评论 #22685747 未加载
thomasahle大约 5 年前
Video here: <a href="https:&#x2F;&#x2F;youtu.be&#x2F;5rPJyrU-WE4" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;5rPJyrU-WE4</a><p>Can anyone explain why people would use text to speech for something like this, when they have perfectly good voices themselves?
评论 #22689249 未加载
评论 #22685825 未加载
评论 #22685993 未加载
评论 #22686297 未加载
评论 #22686648 未加载
评论 #22689679 未加载
评论 #22687358 未加载
评论 #22686232 未加载
deckar01大约 5 年前
&quot;We store a copy of the uploaded image ...&quot;<p>Is this really happening with a &quot;deep network in the browser&quot;? It looks like it is happening on a server, then the 3D result is viewed in a browser.
评论 #22686385 未加载
ijpsud大约 5 年前
Not loading properly for me :( I think server may be being overloaded by HN traffic?
评论 #22685712 未加载
nalaka大约 5 年前
Looks like HN has broken their server. I am getting a &quot;Failed to send request to server!&quot; error when I upload an image.
coding123大约 5 年前
I think we slammed it dead.
评论 #22686196 未加载
michaelt大约 5 年前
This looks impressive - shame there aren&#x27;t any examples larger than postage-stamp-sized in the paper or the video.
awinter-py大约 5 年前
if you rotate it 180 deg Z axis, it&#x27;s like she&#x27;s watching you
评论 #22687717 未加载
h91wka大约 5 年前
Please fix the title of submission. It is &quot; Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild&quot;. No anime examples to be found in the paper :(
评论 #22685980 未加载
评论 #22686291 未加载
itronitron大约 5 年前
<i>because we can</i>