Learning neural implicit surfaces from volume rendering has become popular for multi-view reconstruction. Neural surface reconstruction approaches can recover complex 3D geometry that are difficult for classical Multi-view Stereo (MVS) approaches, such as non-Lambertian surfaces and thin structures. However, one key assumption for these methods is knowing accurate camera parameters for the input multi-view images, which are not always available. In this paper, we present NoPose-NeuS, a neural implicit surface reconstruction method that extends NeuS to jointly optimize camera poses with the geometry and color networks. We encode the camera poses as a multi-layer perceptron (MLP) and introduce two additional losses, which are multi-view feature consistency and rendered depth losses, to constrain the learned geometry for better estimated camera poses and scene surfaces. Extensive experiments on the DTU dataset show that the proposed method can estimate relatively accurate camera poses, while maintaining a high surface reconstruction quality with 0.89 mean Chamfer distance.

翻译：从体渲染中学习神经隐式表面已成为多视图重建的热门方法。神经表面重建方法能够恢复传统多视图立体匹配（MVS）方法难以处理的复杂三维几何结构，例如非朗伯表面和薄层结构。然而，这类方法的关键前提是需预先获知输入多视图图像的精确相机参数，而这一条件往往难以满足。本文提出NoPose-NeuS方法，这是一种扩展NeuS框架的神经隐式表面重建方法，能够联合优化相机位姿、几何网络与颜色网络。我们将相机位姿编码为多层感知机（MLP），并引入多视图特征一致性与渲染深度两个附加损失函数，通过约束学习到的几何信息来优化相机位姿与场景表面的估计。在DTU数据集上的大量实验表明，该方法在保持0.89平均倒角距离的高质量表面重建的同时，能够估计出较为精确的相机位姿。