TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Real time image animation in opencv using first order model

255 pointsby abhas9almost 5 years ago

13 comments

qchrisalmost 5 years ago
I'm a huge fan of this kind of practice, where the code for a paper is all located in a single public repository with build instructions, along with directions for how to cite it. Obviously, it's a little tough to do with some more data-intensive sources (besides GH hosting limits, no one really wants to download 100G of data if they're just trying to clone a repository), but this kind of thing sets a high standard for reproducibility of published results.
评论 #23314453 未加载
评论 #23314544 未加载
rozgoalmost 5 years ago
I&#x27;m working with same model, but in a real-time pipeline developed with GStreamer, Rust and PyTorch:<p><a href="https:&#x2F;&#x2F;twitter.com&#x2F;rozgo&#x2F;status&#x2F;1255961525187235842" rel="nofollow">https:&#x2F;&#x2F;twitter.com&#x2F;rozgo&#x2F;status&#x2F;1255961525187235842</a><p>Live motion transfer test with crappy webcam:<p><a href="https:&#x2F;&#x2F;youtu.be&#x2F;QVRpstP5Qws" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;QVRpstP5Qws</a>
评论 #23317433 未加载
forgingaheadalmost 5 years ago
Very cool, reminds me of Avatarify, which is also based upon the First Order Model work:<p><a href="https:&#x2F;&#x2F;github.com&#x2F;alievk&#x2F;avatarify" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;alievk&#x2F;avatarify</a>
评论 #23315752 未加载
egfxalmost 5 years ago
Pretty cool. Reminds me of <a href="https:&#x2F;&#x2F;github.com&#x2F;yemount&#x2F;pose-animator" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;yemount&#x2F;pose-animator</a><p>I would use it if there was a JavaScript port.
bsaulalmost 5 years ago
How can it generate teeth that look like they fit the picture ???
评论 #23314943 未加载
sriram_malharalmost 5 years ago
Is no one else deeply afraid of this future?
评论 #23315630 未加载
评论 #23315566 未加载
评论 #23315317 未加载
imronalmost 5 years ago
Looks like the file mentioned in this step<p>&gt; gdown --id 1wCzJP1XJNB04vEORZvPjNz6drkXm5AUK<p>Is no longer accessible (too many downloads in too short a time)<p>Edit: For anyone else with the same problem, the file in question is &quot;vox-cpk.pth.tar&quot; which can be found in various places on the internet.
seesawtronalmost 5 years ago
The google colab version is not really real-time, is that correct? It loads pre-recorded video. I guess that is because it is not easy to add realtime feed from camera into browser notebook or what are the limitations there?
villgaxalmost 5 years ago
The paper &amp; final models don&#x27;t to justice for detailed outputs though, but this is still a great model for datasets with no annotations per se.
karakanbalmost 5 years ago
does anyone know if using this tool to generate a music video of famous pictures singing a song would violate any copyrights? it seems like a fun exercise.
sgroppinoalmost 5 years ago
very neat! You can crop and convert to mp4 using ffmpeg: ffmpeg -i test.avi -filter:v &quot;crop=250:250:260:0&quot; out.mp4
throwlaplacealmost 5 years ago
one of the authors is at snap. inquiring minds want to know: will this soon be available in snap camera?
mister_hnalmost 5 years ago
Really cool, but I hoped to see C++ code for OpenCV, not python
评论 #23313227 未加载