Neural implicit surface learning has shown significant progress in multi-view 3D reconstruction, where an object is represented by multilayer perceptrons that provide continuous implicit surface representation and view-dependent radiance. However, current methods often fail to accurately reconstruct reflective surfaces, leading to severe ambiguity. To overcome this issue, we propose Ref-NeuS, which aims to reduce ambiguity by attenuating the importance of reflective surfaces. Specifically, we utilize an anomaly detector to estimate an explicit reflection score with the guidance of multi-view context to localize reflective surfaces. Afterward, we design a reflection-aware photometric loss that adaptively reduces ambiguity by modeling rendered color as a Gaussian distribution, with the reflection score representing the variance. We show that together with a reflection direction-dependent radiance, our model achieves high-quality surface reconstruction on reflective surfaces and outperforms the state-of-the-arts by a large margin. Besides, our model is also comparable on general surfaces.
翻译:神经元隐式表面学习已经在多视角3D重建中显示出了显著进展,其中对象由提供连续隐式表面表示和视角相关辐射的多层感知机表示。然而,当前的方法往往无法准确重建反射表面,导致严重的模糊度。为了克服这个问题,我们提出了 Ref-NeuS,它旨在通过削弱反射表面的重要性来减少模糊度。具体而言,我们利用异常检测器来估计明确的反射分数,并在多视角上下文的指导下定位反射表面。其后,我们设计了一个反射感知光度损失,通过将渲染颜色建模为高斯分布,并将反射分数表示为方差,自适应地减少了模糊度。我们展示了,与反射方向相关的辐射一起, 我们的模型在反射表面的高质量表面重建上表现出色,并且在通用表面上也表现得相当不错, 且优于现有技术。