arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.06231cs.CV
收藏

用于多细节层次的潜在隐式三维形状模型

A Latent Implicit 3D Shape Model for Multiple Levels of Detail

CVLab, EPFL(EPFL计算机视觉实验室);Max Planck Institute for Informatics(马克斯·普朗克信息学研究所)

Benoit Guillard, Marc Habermann, Christian Theobalt, Pascal Fua

AI总结:

本文提出一种多尺度、带宽受限的潜在条件隐式神经形状模型,可在单一网络中支持多细节层次并保证表面平滑,重建质量媲美单层次SOTA。

摘要:

隐式神经表示将特定于形状的潜在代码和三维坐标映射到其对应的有符号距离(SDF)值。然而,这种方法只能提供单一的细节层次。可以通过浅层网络模拟较低的细节层次,但生成的形状通常不够平滑。另一些网络设计则提供多个细节层次,但仅限于对单个对象进行过拟合。为解决这一问题,我们提出了一种新的形状建模方法,该方法支持多个细节层次,并保证每个层次都具有平滑表面。其核心是,我们为一种多尺度、带宽受限的神经架构引入了新颖的潜在条件机制。这形成了对多个形状的深度参数化,其中早期层可快速输出近似的SDF值。这使得能够在单一网络内平衡速度与精度,并提高隐式场景渲染的效率。我们证明,通过限制网络带宽,可以在所有细节层次上保持平滑表面。在更精细的层次上,重建质量与仅限于单一细节层次的最先进模型相当。

英文摘要:

Implicit neural representations map a shape-specific latent code and a 3D coordinate to its corresponding signed distance (SDF) value. However, this approach only offers a single level of detail. Emulating low levels of detail can be achieved with shallow networks, but the generated shapes are typically not smooth. Alternatively, some network designs offer multiple levels of detail, but are limited to overfitting a single object. To address this, we propose a new shape modeling approach, which enables multiple levels of detail and guarantees a smooth surface at each level. At the core, we introduce a novel latent conditioning for a multiscale and bandwith-limited neural architecture. This results in a deep parameterization of multiple shapes, where early layers quickly output approximated SDF values. This allows to balance speed and accuracy within a single network and enhance the efficiency of implicit scene rendering. We demonstrate that by limiting the bandwidth of the network, we can maintain smooth surfaces across all levels of detail. At finer levels, reconstruction quality is on par with the state of the art models, which are limited to a single level of detail.

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。

↑