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。

NPGA: Neural Parametric Gaussian Avatars – high-fidelity digital faces

60 点作者 samspenc12 个月前

4 条评论

kaivi12 个月前
Their github page has some videos: <a href="https:&#x2F;&#x2F;simongiebenhain.github.io&#x2F;NPGA&#x2F;" rel="nofollow">https:&#x2F;&#x2F;simongiebenhain.github.io&#x2F;NPGA&#x2F;</a>
vessenes12 个月前
Um, wow. These are really, really good. They are not perfect, but the improvements on fidelity, open mouth, eyes over a GAN-based approach are .. real high.<p>This is the first paper I’ve seen with videos that compare a person with a re-render side by side, and it’s a nice way to see what the model’s good at, and what it’s not.<p>Some perf numbers (which they say are unoptimized): 30-60 hrs on a 3080 for the avatar model, and rendering in the 20-40fps range on the same hardware. Basically good enough for a commercial implementation. They don’t mention latency of the CNN side that I can find, which is obviously a big question for chat scenarios, although not a big deal for pre-rendered scenes.
评论 #40530500 未加载
supportengineer12 个月前
In the novel <i>Snow Crash</i>, one of the characters, Juanita, does just this - she is known for making realistic facial expressions possible in the metaverse.
azinman212 个月前
Given the now clear abuse potential (and other issues surrounding AI generally), why do papers like this discuss the motivation as if it’s a for sure requirement to do such work?<p>“The creation of high-fidelity, digital versions of human heads is an important stepping stone in the process of further integrating virtual components into our everyday lives.”<p>It’s not clear to me that’s a desirable outcome.
评论 #40531849 未加载
评论 #40532026 未加载