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。

Photo Wake-Up: 3D Character Animation from a Single Photo

392 点作者 lun4r超过 6 年前

15 条评论

aantix超过 6 年前
It’s so frustrating when the code or a binary isn’t released and we can’t play with this ourselves.<p>What’s the point of publicly releasing a paper with no real proof of work? They could be faking the algorithm.
评论 #18756686 未加载
评论 #18753156 未加载
kennyadam超过 6 年前
At first I thought it was something that could be done in real time. Like, you walk up to any painting with the AR glasses on, do the gesture and it would extract a figure and animate it. On closer inspection, the artworks are also virtual in their example videos. I was hoping they would be real, it feel less impressive when none of it is really present.
pndy超过 6 年前
It&#x27;s amazing but also creepy because characters still retain the non-animated face and&#x2F;or limbs like in Messi example; making faces moving seems to be logical next step for this technology.
visarga超过 6 年前
I&#x27;m wondering how they texture the backside of animated characters?
评论 #18750673 未加载
kamalkishor1991超过 6 年前
did they release code also? I could not find any link anywhere?
nmstoker超过 6 年前
Very impressive. Not to be a cynic, but how long before someone starts turning people inappropriately into frog marching saluting Nazis?! Or giving them an unfortunate Fortnite &quot;bounce&quot;.<p>I haven&#x27;t read the paper, but am curious how they get the face profile right (given the information is absent in the 2D source). Perhaps they set that manually or some kind of average face, but if it&#x27;s off it would be quite noticeable.
评论 #18751205 未加载
jibolso超过 6 年前
This is neat. Very neat, good implementation and interesting applications.
pohl超过 6 年前
I was surprised at how quickly I went from slack-jawed amazement to wondering why the creators were so enamored with making a character run out of the frame that they never demonstrated using this to animate in context.
评论 #18758705 未加载
dlhavema超过 6 年前
Looks super cool. I wonder if multiple subjects in the same photo could be animated. I sorta expected that from the picture with the Beatles ( assuming that gang of 4 Brittish looking guys was them )
评论 #18750887 未加载
peter_d_sherman超过 6 年前
a-ha - Take On Me (Official Music Video) <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=djV11Xbc914" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=djV11Xbc914</a>
garfieldnate超过 6 年前
I don&#x27;t know if anyone else here has seen _The Ring_, but the little girl walking out of the screen kind of freaked me out!
egfx超过 6 年前
Oh great. Now we can make The Ring scene come alive. Merry Christmas.
评论 #18750717 未加载
Awtem超过 6 年前
Great, now you can have your own custom video game avatar from a single picture of yourself... gaming industry will love this
评论 #18751102 未加载
tugberkk超过 6 年前
Am I the only one who is scared from these technological advances?
评论 #18752028 未加载
bsenftner超过 6 年前
This is a series of known techniques assembled in a visually engaging manner, but is ultimately just a dumb gimmick. * Ability to go from image to model - multiple open source options * Ability to to from image to rigged figure model - multiple open source options * motion capture animation playback - trivial Unless this is instantaneous, which it is not, it&#x27;s an attention seeking toy with no original ip.
评论 #18753186 未加载