SuperGaussian:重新利用视频模型实现三维超分辨率
SuperGaussian: Repurposing Video Models for 3D Super Resolution
AI总结:
提出SuperGaussian方法,重新利用预训练视频模型进行三维超分辨率,结合三维整合生成高质量高斯溅射模型,显著提升三维模型保真度。
摘要:
我们提出了一种简单、模块化且通用的方法,通过添加几何和外观细节来上采样粗糙的三维模型。尽管生成式三维模型现已存在,但它们尚未达到图像和视频领域中对应模型的质量。我们证明,直接重新利用现有的(预训练的)视频模型进行三维超分辨率是可能的,从而绕过了高质量三维训练模型大型存储库短缺的问题。我们描述了如何重新利用视频上采样模型(这些模型并非三维一致的)并将其与三维整合相结合,以产生三维一致的结果。作为输出,我们生成高质量的高斯溅射模型,这些模型以物体为中心且有效。我们的方法是类别无关的,可以轻松集成到现有的三维工作流程中。我们在各种三维输入上评估了我们提出的SuperGaussian,这些输入在复杂性和表示形式(例如,高斯溅射或神经辐射场)方面均多样化,并证明我们的简单方法显著提高了最终三维模型的保真度。详情请访问我们的项目网站:supergaussian.github.io
英文摘要:
We present a simple, modular, and generic method that upsamples coarse 3D models by adding geometric and appearance details. While generative 3D models now exist, they do not yet match the quality of their counterparts in image and video domains. We demonstrate that it is possible to directly repurpose existing (pretrained) video models for 3D super-resolution and thus sidestep the problem of the shortage of large repositories of high-quality 3D training models. We describe how to repurpose video upsampling models, which are not 3D consistent, and combine them with 3D consolidation to produce 3D-consistent results. As output, we produce high quality Gaussian Splat models, which are object centric and effective. Our method is category agnostic and can be easily incorporated into existing 3D workflows. We evaluate our proposed SuperGaussian on a variety of 3D inputs, which are diverse both in terms of complexity and representation (e.g., Gaussian Splats or NeRFs), and demonstrate that our simple method significantly improves the fidelity of the final 3D models. Check our project website for details: supergaussian.github.io
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。