Recent progress in neural implicit functions has set new state-of-the-art in reconstructing high-fidelity 3D shapes from a collection of images. However, these approaches are limited to closed surfaces as they require the surface to be represented by a signed distance field. In this paper, we propose NeAT, a new neural rendering framework that can learn implicit surfaces with arbitrary topologies from multi-view images. In particular, NeAT represents the 3D surface as a level set of a signed distance function (SDF) with a validity branch for estimating the surface existence probability at the query positions. We also develop a novel neural volume rendering method, which uses SDF and validity to calculate the volume opacity and avoids rendering points with low validity. NeAT supports easy field-to-mesh conversion using the classic Marching Cubes algorithm. Extensive experiments on DTU, MGN, and Deep Fashion 3D datasets indicate that our approach is able to faithfully reconstruct both watertight and non-watertight surfaces. In particular, NeAT significantly outperforms the state-of-the-art methods in the task of open surface reconstruction both quantitatively and qualitatively.
翻译:近期神经隐式函数的进展为从图像集合中重建高保真3D形状设置了最新的实时表现。然而,这些方法限制了仅能处理封闭表面,因为需要用符号距离场来表示表面。本论文提出了NeAT,是一种新的神经渲染框架,可以从多视图图像中学习任意拓扑的隐式表面。NeAT将3D表面表示为带有有效分支估计查询位置的表面存在概率的符号距离函数(SDF)的级集。我们还开发了一种新颖的神经体渲染方法,利用SDF和有效性计算体的不透明度,避免渲染具有低有效性的点。NeAT支持使用经典的Marching Cubes算法轻松进行场到网格转换。在DTU、MGN和Deep Fashion 3D数据集上进行的广泛实验表明,我们的方法能够忠实地重建闭合和非闭合表面。特别是,在开放表面重建任务中,NeAT在定量和定性上都显着优于最先进的方法。