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。

3-Sweep: Extracting Editable Objects from a Single Photo [video]

354 点作者 rellik超过 11 年前

30 条评论

mwsherman超过 11 年前
The key here is really complementary use of ‘what humans are good at’ and ‘what machines are good at’.<p>In this case, it’s fair to say the machine, by analyzing pixels, can’t figure out perspective very well. The human can do that just fine, given an interface mechanism.<p>The machine is good at detecting edges and seeing similarity between pixels. Given hints from the human that ‘this point is within an object’ and here is the perspective, the machine can infer the limits of the object based on edges&#x2F;colors and project it into 3 dimensions. Amazing.
评论 #6364002 未加载
评论 #6364727 未加载
olympus超过 11 年前
I&#x27;m not a HN etiquette stickler, and I&#x27;m not accusing anyone of any foul play, but the actual YouTube video was submitted 17 hours prior to this post: <a href="https://news.ycombinator.com/item?id=6358080" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=6358080</a><p>This is just in case you want to throw a few upvotes their way for being first. This also illustrates that late night (PDT&#x2F;UTC -8) posts don&#x27;t get a whole lot of votes and proper timing is crucial to getting lots of votes.
评论 #6364733 未加载
krisoft超过 11 年前
What I was thinking all along: &quot;Oh come on! It can&#x27;t be this perfect, show me where it fails.&quot; And they did!<p>This is indeed magic. I&#x27;m so happy to live in this age, and be part of the &quot;Sorcerers&#x27; Guild&quot;.
评论 #6363914 未加载
DocSavage超过 11 年前
The paper is not out yet, but you can read the abstract here:<p><a href="http://www.faculty.idc.ac.il/arik/site/3Sweep.asp" rel="nofollow">http:&#x2F;&#x2F;www.faculty.idc.ac.il&#x2F;arik&#x2F;site&#x2F;3Sweep.asp</a>
breckinloggins超过 11 年前
If you marked shadows and associated them with their source, could you then recover the light source(s) and be able to remove the baked shadows and recast them in real time?<p>Also, with the shiny objects, could you specify the material properties and have it &quot;back out&quot; the reflection such that the reflection was recomputed as you moved the shape around?
评论 #6363965 未加载
swamp40超过 11 年前
WOW.<p>Forget the Photoshop stuff, this needs to be integrated with 3D printing <i>immediately</i>.<p>Spit out a design file into Tinkercad[1] for some minor adjustments and BAM, you&#x27;ve made a printable 3D model.<p>[1] <a href="https://tinkercad.com/" rel="nofollow">https:&#x2F;&#x2F;tinkercad.com&#x2F;</a>
评论 #6366557 未加载
moocowduckquack超过 11 年前
I want this + i❤sketch now, but unfortunately I suspect that jumping up and down and shouting isn&#x27;t likely to help.<p><a href="http://www.dgp.toronto.edu/~shbae/ilovesketch.htm" rel="nofollow">http:&#x2F;&#x2F;www.dgp.toronto.edu&#x2F;~shbae&#x2F;ilovesketch.htm</a>
评论 #6364010 未加载
alxbrun超过 11 年前
Wow, super impressive. And meanwhile, Silicon Valley is working on the gazillionth social photo sharing app.
评论 #6364440 未加载
Raphmedia超过 11 年前
This is sorcery!<p>This technology is awesome. If it&#x27;s as user friendly as they make it looks, I could see a lot of application for that!
评论 #6363824 未加载
dharma1超过 11 年前
most impressive thing for me about this demo is how good the shape detection is (seems way better than magnetic lasso in Photoshop), and how they brought different pieces of separate technologies together to such a fluid experience. And how the presenter sounds about 12.<p>These guys&#x2F;girls know what they&#x27;re doing.
评论 #6370838 未加载
martindale超过 11 年前
This is the single most impressive example of image processing I&#x27;ve seen to date.
评论 #6363973 未加载
评论 #6367734 未加载
lsh超过 11 年前
This seems quite similar to this presented in 2011: <a href="https://www.youtube.com/watch?v=hmzPWK6FVLo" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=hmzPWK6FVLo</a><p><a href="http://www.kevinkarsch.com/publications/sa11.html" rel="nofollow">http:&#x2F;&#x2F;www.kevinkarsch.com&#x2F;publications&#x2F;sa11.html</a>
tbatchelli超过 11 年前
It looks so simple, yet my limited understanding of image processing tells me this requires a ton of research and technology. The pace of innovation is staggering!
atopuzov超过 11 年前
I wish I had the time to sit down and understand all the math and algorithms behind this. It&#x27;s awesome.
jostmey超过 11 年前
I am skeptical, although I remain hopeful that my skepticism is misplaced. The &quot;software&quot; somehow seems to know what pattern of colors should exist on the other side of the object. Can someone explain to us how this aspect of the software works?
评论 #6363934 未加载
评论 #6363930 未加载
baddox超过 11 年前
Is there a reason many of these crazy image processing technologies never seem to have actual demos or releases? The only exception I can think of it the &quot;smart erase&quot; idea, which has been implemented in Photoshop as well as Gimp.
评论 #6364311 未加载
评论 #6365318 未加载
评论 #6364155 未加载
snogglethorpe超过 11 年前
A lot of cool rendering&#x2F;modeling research seems amazingly well-suited for the film industry and this is a perfect example ... besides the obvious applications in making CGI versions of real-world scenes, you can just imagine the director saying &quot;oh no, that lamp is in the wrong location in all that footage... move it (without reshooting)!&quot;<p>I wonder if it&#x27;s just a coincidence, or whether the mega-bucketloads of money the film industry throws at CGI are a major factor in funding related research even in academia?
评论 #6367726 未加载
zem超过 11 年前
this is one of the most impressive things i&#x27;ve seen in a while.
zxcvvcxz超过 11 年前
Question for the entrepreneurs: how would one monetize such a cool algorithm? I come across plenty of cool stuff like this, but without any idea how they can solve real problems.
评论 #6367773 未加载
评论 #6365848 未加载
jack-r-abbit超过 11 年前
Also awesome is that it handles the background replacement so well. This could also be used to just remove an ugly lamp post, telephone pole, etc from an otherwise good photo. (assuming you can remove objects and resave the image)<p>Edit: I am aware that Photoshop has some of this available. I&#x27;ve not played with it so I don&#x27;t know how they compare.
评论 #6363969 未加载
评论 #6364949 未加载
评论 #6364102 未加载
hazz超过 11 年前
This is amazing. My first thought is this could allow F1 teams to get a much better idea of what new packages their competitors are bringing to races early on just by looking at photos and video footage and modelling the new parts.
评论 #6364011 未加载
TullamoreDude超过 11 年前
This indeed is very impressing and I see the how much work passion is into this project.But I still have to say it almost only about round or cylindrical objects, there is still a long way to go
评论 #6365619 未加载
voltagex_超过 11 年前
Is it too much to hope that this tech will be implemented in a program that&#x27;s within an &quot;average&quot; user&#x27;s budget? (i.e. non-enterprise).
deadfall超过 11 年前
I think this is really impressive. Do you think it will be years before this actually gets used in public 3D modelling tools?<p>I vote for this to be used with 3D printer
EGreg超过 11 年前
This is awesome - but how do they reconstruct the backgrounds that the objects previously obscured? There must be more photos?
评论 #6364104 未加载
Beltiras超过 11 年前
This video is currently unavailable. Anyone else getting static@youtube?
pjgomez超过 11 年前
Simply astonishing... imho this technology is revolutionary.
agumonkey超过 11 年前
A worthy successor to SketchPad, beautiful user interface.
DavidPlumpton超过 11 年前
I read this as &quot;from a single photon&quot;
scoofy超过 11 年前
I&#x27;m going to need to buy more filament...