arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2211.11971cs.CV
收藏

基于结构光的多视点神经元表面重建

Multi-View Neural Surface Reconstruction with Structured Light

Preferred Networks, Inc.(Preferred Networks 公司)

Chunyu Li, Taisuke Hashimoto, Eiichi Matsumoto, Hiroharu Kato

摘要:

基于可微分绘制的三维物体重建是计算机视觉的一个研究热点。基于DR的方法通过优化形状和外观并实现高视觉再现性来最小化渲染图像和目标图像之间的差异。然而,由于几何模糊性,大多数方法对于无纹理对象的表现都很差,这意味着多个形状在这样的对象中可以具有相同的渲染结果。为了克服这个问题,我们引入主动传感与结构光(SL)的多视角三维物体重建的基础上DR学习未知的几何形状和外观的任意场景和相机的姿态。更具体地说,我们的框架利用结构光计算的不同视图中的像素之间的对应关系作为基于DR的隐式表面,颜色表示和相机姿态优化中的附加约束。由于摄像机姿态可以同时优化,我们的方法实现了高的重建精度在无纹理区域,并减少了摄像机姿态校准,这是传统的SL为基础的方法所需的努力。合成和真实数据的实验结果表明,我们的系统优于传统的DR和SL为基础的方法,在高质量的表面重建,特别是具有挑战性的对象与无纹理或有光泽的表面。

英文摘要:

Three-dimensional (3D) object reconstruction based on differentiable rendering (DR) is an active research topic in computer vision. DR-based methods minimize the difference between the rendered and target images by optimizing both the shape and appearance and realizing a high visual reproductivity. However, most approaches perform poorly for textureless objects because of the geometrical ambiguity, which means that multiple shapes can have the same rendered result in such objects. To overcome this problem, we introduce active sensing with structured light (SL) into multi-view 3D object reconstruction based on DR to learn the unknown geometry and appearance of arbitrary scenes and camera poses. More specifically, our framework leverages the correspondences between pixels in different views calculated by structured light as an additional constraint in the DR-based optimization of implicit surface, color representations, and camera poses. Because camera poses can be optimized simultaneously, our method realizes high reconstruction accuracy in the textureless region and reduces efforts for camera pose calibration, which is required for conventional SL-based methods. Experiment results on both synthetic and real data demonstrate that our system outperforms conventional DR- and SL-based methods in a high-quality surface reconstruction, particularly for challenging objects with textureless or shiny surfaces.

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。

↑