ADM-201 dump PMP dumps pdf SSCP exam materials CBAP exam sample questions

基于物理的图像和视频编辑 – 译学馆
未登录,请登录后再发表信息
最新评论 (0)
播放视频

基于物理的图像和视频编辑

Physics-based Image and Video Editing | Two Minute Papers #187

亲爱的学霸们 这是由Károly Zsolnai-Fehér带来的两分钟论文
Dear Fellow Scholars, this is Two Minute Papers with Károly Zsolnai-Fehér.
本篇论文介绍的是通过添加新对象或编辑物理属性
This work is about changing already existing images and videos by adding new objects to
来更改现有的图像和视频
them, or editing their physical attributes.
这些可编辑的属性包括重力 质量 刚度 我们甚至可以往场景中
These editable attributes include gravity, mass, stiffness, or we can even add new physical
添加新的力
forces to the scene.
例如 我们可以改变这幅达利的画中的手表的钢度
For instance, we can change the stiffness of the watches in this Dalí painting and
并以此创作一个动画
create an animation from it.
从绘画得到动画 并使其精确展现物理属性
Physically accurate animations from paintings.
该是多么酷啊!
How cool is that?
这几乎接近科幻小说的疯狂程度了
This is approaching science fiction levels of craziness.
我们可以通过向场景添加虚拟风力效果 来动画模拟静止的晾衣绳
Animating a stationary clothesline by adding a virtual wind effect to the scene, or bending
或者通过改变质量 来使桥梁弯曲
a bridge by changing its mass is also a possibility.
当我看过这篇论文时 我第一反应是“你在逗我么?
The first reaction I had when I’ve looked at this work was “are you kidding me? you
怎么可能编辑照片!”
can’t edit a photograph!”.
特别是 我已经看过很多早期的工作试图做类似的尝试
Especially that I’ve seen plenty of earlier works that tried to do something similar but
但每一次的结果都有太多局限性 无法应用于现实世界
each time the limitations were just too crippling for real-world usage.
而另一个根本性的问题是—对于用户来说 这到底多难使用?
And the other ultimate question is always – how much user interaction does this need?
是很简单呢?还是非常麻烦?
Is this trivial to use, or is it a laborious process?
我们需要做的是尽量突显出要操作对象的轮廓
What we need to do is roughly highlight the outline of the object that we’d like to manipulate.
该算法使用先前发布的一项技术来准确捕获轮廓
The algorithm uses a previously published technique to make sure that the outlines are
并在所选区域中尝试创建3D数字模型
accurately captured, and then tries to create a 3D digital model from the selected area.
下一步 需要对照图像或视频输入 校准3D模型
We need one more step where we align the 3D model to the image or video input.
最后 属性的更改和编辑并没有在视频镜头中进行 而是
Finally, the attribute changes and edits take place not on the video footage, but on this
通过物理模拟技术在3D模型上进行
3D model through a physics simulation technique.
这项工作通过一些杀手级应用程序 将新旧技术重新组合
A truly refreshing combination of old and new techniques with some killer applications.
炒鸡喜欢哦!
Loving it!
其中最大的挑战就是 在这些更改以后 必须保留
The biggest challenge is to make sure that the geometry and the visual consistency of
场景的几何效果与视觉感的一致性
the scene is preserved through these changes.
论文中讨论了很多细节 你一定要看看
There are plenty of details discussed in the paper, make sure to have a look at that,
论文链接在视频描述栏
the link to it is available in the video description.
随着对2D照片到3D模型的生成算法的改进 在不久的将来 这些
As these 2D photo to 3D model generator algorithms improve, so will the quality of these editing
编辑技术的质量也会提高
techniques in the near future.
我们以前的视频有关于这个话题的 一定要看看
Our previous episode was on this topic, make sure to have a look at that.
此外 对于这个快速发展的领域 如果您想获得更多最新最酷的
Also, if you would like to get more updates on the newest and coolest works in this rapidly
论文更新 请务必订阅 并点击铃铛图标 以便收到
improving field, make sure to subscribe and click the bell icon to be notified when new
两分钟论文的视频更新通知
Two Minute Papers videos come up.
感谢您的收看和大力支持 我们下期再见!
Thanks for watching and for your generous support, and I’ll see you next time!

发表评论

译制信息
视频概述

AI又放大招了,这次要通过物理属性对2D图像和视频进行编辑了

听录译者

收集自网络

翻译译者

[B]无牙无耳

审核员

审核团O

视频来源

https://www.youtube.com/watch?v=bVGubOt_jLI

相关推荐