Customize Consent Preferences

We use cookies to help you navigate efficiently and perform certain functions. You will find detailed information about all cookies under each consent category below.

The cookies that are categorized as "Necessary" are stored on your browser as they are essential for enabling the basic functionalities of the site. ... 

Always Active

Necessary cookies are required to enable the basic features of this site, such as providing secure log-in or adjusting your consent preferences. These cookies do not store any personally identifiable data.

No cookies to display.

Functional cookies help perform certain functionalities like sharing the content of the website on social media platforms, collecting feedback, and other third-party features.

No cookies to display.

Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics such as the number of visitors, bounce rate, traffic source, etc.

No cookies to display.

Performance cookies are used to understand and analyze the key performance indexes of the website which helps in delivering a better user experience for the visitors.

No cookies to display.

Advertisement cookies are used to provide visitors with customized advertisements based on the pages you visited previously and to analyze the effectiveness of the ad campaigns.

No cookies to display.

0

在即将召开的欧洲计算机视觉大会(ECCV 2024)上,来自南洋理工大学S-Lab、上海AI Lab和北京大学的研究团队带来了一项创新性成果——原生3D LDM(Latent Diffusion Model)生成框架,名为Latent Neural Fields 3D Diffusion(LN3Diff)。这一框架旨在解决当前3D生成模型的可拓展性差、训练效率低和泛化能力不足等问题。

研究背景与挑战

神经渲染技术在新视角合成、3D编辑和物体生成等领域取得了显著进步,但通用的3D生成框架仍相对匮乏。现有方法如基于SDS(Scene Description Signal)的蒸馏和多视图生成加Feedforward重建,分别面临优化时间长和多样性不足的挑战,限制了3D AI生成内容的性能和自由度。

LN3Diff:3D生成的新突破

为克服这些限制,研究团队引入了LDM框架到3D生成中,通过在3D隐空间直接进行diffusion采样,实现快速、高质量的3D内容生成。他们的方法,LN3Diff,是一个适用于任意神经场的通用框架,旨在提高生成效率和质量,同时保持良好的控制性。

3D-aware VAE:信息压缩的优化

LN3Diff的核心是3D-aware VAE,它以多视图图像、深度图和相机信息为输入,进行3D-aware attention运算,以保持3D一致性。在解码器端,优化的信息压缩技术进一步提升了模型的性能。

大规模训练与基准测试

该框架在Objaverse数据集上进行了大规模训练,并在多个基准测试中表现出色,同时具备更快的推理速度。这一进步对于推动3D人工智能内容生成(3D AIGC)的性能和自由度具有重要意义。

论文与代码资源

研究论文的项目主页位于https://nirvanalan.github.io/projects/ln3diff/,代码已经公开在GitHub上,可访问https://github.com/NIRVANALAN/LN3Diff获取。此外,研究者还提供了Gradio演示,供用户交互体验LN3Diff的3D生成效果。

论文作者

论文第一作者兰宇时是南洋理工大学的博士生,师从Chen Change Loy教授。他的主要研究兴趣集中在基于神经渲染的3D生成模型和3D重建与编辑。

未来展望

这项工作为3D生成模型的研究开辟了新的道路,有望在游戏、虚拟现实、建筑和产品设计等领域产生广泛影响。随着技术的不断进步,我们期待看到更多高效、灵活的3D生成工具,进一步推动人工智能与3D内容创作的融合。

【source】https://www.jiqizhixin.com/articles/2024-08-26-6

Views: 1

0

发表回复

您的邮箱地址不会被公开。 必填项已用 * 标注