InfoNorm：基于法线互信息塑形的稀疏视角重建
InfoNorm: Mutual Information Shaping of Normals for Sparse-View Reconstruction
AI总结：
针对复杂室内场景稀疏视角重建中几何先验依赖问题，提出通过增强相关表面点法线互信息来正则化SDF隐式表面建模，消除泛化偏差，提升重建质量。
摘要：
从多视角图像进行三维表面重建对于场景理解和交互至关重要。然而，复杂的室内场景由于观测有限而带来模糊性等挑战。近年来，隐式表面表示方法，如神经辐射场（NeRFs）和符号距离函数（SDFs），利用各种几何先验来弥补观测信息的不足。然而，它们的性能严重依赖于预训练几何估计模型的质量。为了减轻这种依赖，我们提出通过显式鼓励高度相关场景点的表面法线之间的互信息来正则化几何建模。通过这种方式，几何学习过程受到来自噪声（一阶）几何先验的二阶相关性的调制，从而消除了因泛化能力差而产生的偏差。此外，我们引入了一种简单而有效的方案，利用语义和几何特征来识别相关点，并相应地增强它们的互信息。所提出的技术可以作为基于SDF的神经表面表示的插件。我们的实验证明了该方法在提高主流先进方法的表面重建质量方面的有效性。我们的代码可在以下网址获取：https://github.com/Muliphein/InfoNorm。
英文摘要：
3D surface reconstruction from multi-view images is essential for scene understanding and interaction. However, complex indoor scenes pose challenges such as ambiguity due to limited observations. Recent implicit surface representations, such as Neural Radiance Fields (NeRFs) and signed distance functions (SDFs), employ various geometric priors to resolve the lack of observed information. Nevertheless, their performance heavily depends on the quality of the pre-trained geometry estimation models. To ease such dependence, we propose regularizing the geometric modeling by explicitly encouraging the mutual information among surface normals of highly correlated scene points. In this way, the geometry learning process is modulated by the second-order correlations from noisy (first-order) geometric priors, thus eliminating the bias due to poor generalization. Additionally, we introduce a simple yet effective scheme that utilizes semantic and geometric features to identify correlated points, enhancing their mutual information accordingly. The proposed technique can serve as a plugin for SDF-based neural surface representations. Our experiments demonstrate the effectiveness of the proposed in improving the surface reconstruction quality of major states of the arts. Our code is available at: \url{https://github.com/Muliphein/InfoNorm}.
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。
