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。

Nvidia Kaolin Wisp: a PyTorch library to work with neural fields

83 点作者 lnyan将近 3 年前

5 条评论

fxtentacle将近 3 年前
It&#x27;s a CUDA accelerated toolkit for storing and tracing volume data.<p>In my opinion, this one is pretty pointless because everyone who uses Nerf or similar technology in a game or end user product will need AMD and Intel GPU support, so CUDA is a no-go. And researchers can just copy a 200 line PyTorch model of they want to build a customized Nerf. Plus if you do that, you get the production export to onnx for free.<p>In short, I can&#x27;t imagine any case where using a CUDA-specific closed source library would be superior to using readily available PyTorch scripts.
评论 #32536143 未加载
评论 #32536698 未加载
评论 #32537694 未加载
评论 #32537470 未加载
评论 #32536242 未加载
hnarayanan将近 3 年前
What is a neural field?
评论 #32539736 未加载
holografix将近 3 年前
Is there a way to generate industry standard 3D models from NeRF? Say something that unity or unreal can use?
评论 #32536585 未加载
rektide将近 3 年前
google has been putting significant work into a neural fields extension of their very popular Jax machine-learning toolkit too, <a href="https:&#x2F;&#x2F;github.com&#x2F;google-research&#x2F;jax3d" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;google-research&#x2F;jax3d</a>
keepquestioning将近 3 年前
This appears to be a gamechanger