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。

N-Dimensional Gaussians for Fitting of High Dimensional Functions

67 点作者 jasondavies大约 1 年前

3 条评论

vessenes大约 1 年前
When I think of turning sequences of images into gaussians, I think of the difficulty of getting generalizable information that can be re-rendered out of the pipeline; textures and lighting, basically. From the description at the top of the paper, where they mention adding dimensions for things like albedo, I got excited.<p>But the demos don&#x27;t do any re-rendering &#x2F; change of lighting &#x2F; etc, so I can&#x27;t tell if this paper is just a &#x27;super high render quality at same training time&#x27; paper, which is of course great to have, or if it has a shot at being extended to get us scenes that can be adjusted as to lighting and texture in-engine.<p>Any experts care to chime in?
评论 #40422779 未加载
评论 #40396147 未加载
评论 #40390533 未加载
3abiton大约 1 年前
This problem specifically (3D reconstruction with representation fitting) is really an overfitting nightmare, they just adapted to it not really overcame it. Nonetheless interesting work.
评论 #40422879 未加载
评论 #40393287 未加载
hackandthink大约 1 年前
I expected Gaussian processes.<p>Can someone relate this to Gaussian processes?
评论 #40394702 未加载
评论 #40393305 未加载