Color-NeuS: Reconstructing Neural Implicit Surfaces with Color
This addresses the need for high-quality mesh and color reconstruction in computer vision, particularly for applications like object scanning, but it is incremental as it builds on existing neural implicit surface methods.
The paper tackles the problem of reconstructing object surfaces with color from multi-view images or monocular video, achieving results that surpass existing methods in tasks with occlusions and lighting shifts, and performing well on public datasets like DTU, BlendedMVS, and OmniObject3D.
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.