The reconstruction of object surfaces from multi-view images or monocular video is a fundamental issue in computer vision. However, much of the recent research concentrates on reconstructing geometry through implicit or explicit methods. In this paper, we shift our focus towards reconstructing mesh in conjunction with color. We remove the view-dependent color from neural volume rendering while retaining volume rendering performance through a relighting network. Mesh is extracted from the signed distance function (SDF) network for the surface, and color for each surface vertex is drawn from the global color network. To evaluate our approach, we conceived a in hand object scanning task featuring numerous occlusions and dramatic shifts in lighting conditions. We've gathered several videos for this task, and the results surpass those of any existing methods capable of reconstructing mesh alongside color. Additionally, our method's performance was assessed using public datasets, including DTU, BlendedMVS, and OmniObject3D. The results indicated that our method performs well across all these datasets. Project page: https://colmar-zlicheng.github.io/color_neus.

翻译：从多视角图像或单目视频中重建物体表面是计算机视觉中的一个基本问题。然而，近期研究大多集中于通过隐式或显式方法重建几何结构。本文中，我们将重点转向结合颜色的网格重建。我们通过一个重光照网络去除神经体渲染中的视角相关颜色，同时保留体渲染性能。从有符号距离函数（SDF）网络中提取表面网格，并从全局颜色网络中为每个表面顶点获取颜色。为评估该方法，我们设计了一项手部抓取物体扫描任务，该任务包含大量遮挡和剧烈光照变化。我们为此任务收集了多个视频，其结果优于任何现有能够同时重建网格和颜色的方法。此外，我们在公开数据集（包括DTU、BlendedMVS和OmniObject3D）上评估了该方法性能。结果表明，该方法在所有数据集中均表现良好。项目页面：https://colmar-zlicheng.github.io/color_neus。