Mobile Photometric Stereo with Keypoint-Based SLAM for Dense 3D Reconstruction
Mobile Photometric Stereo with Keypoint-Based SLAM for Dense 3D Reconstruction
复制标题
DOI：
10.1109/3dv.2019.00069
复制
发表时间：
2019-09
期刊：
影响因子：
--
通讯作者：
R. Maxence;Hideaki Uchiyama;Hiroshi Kawasaki;D. Thomas;Vincent Nozick;H. Saito
中科院分区：
文献类型：
--
作者：
R. Maxence;Hideaki Uchiyama;Hiroshi Kawasaki;D. Thomas;Vincent Nozick;H. Saito
标准的光度立体是一种在具有移动光源的静态相机的假设下使用光变化来密集地重建物体表面的技术。在这项工作中，我们使用光度立体重建密集的3D场景，同时移动相机和灯光。在这种非静态情况下，需要相机姿态以及每个帧的像素之间的对应关系以应用光度立体。ORB-SLAM是一种可用于估计相机姿态的技术。为了检索对应关系，我们的想法是从一个稀疏的3D网格ORB SLAM获得，然后使用多视图光度一致性的平面扫描方法来加密网格。通过将ORB-SLAM和光度立体相结合，可以使用现成的智能手机及其嵌入式手电筒重建密集的3D场景。请注意，SLAM系统通常与无纹理对象斗争，这在我们的方法中通过光度立体有效地补偿。实验结果表明，我们提出的方法给出了更好的结果比SLAM单独或COLMAP，特别是对部分无纹理的表面。
The standard photometric stereo is a technique to densely reconstruct objects' surfaces using light variation under the assumption of a static camera with a moving light source. In this work, we use photometric stereo to reconstruct dense 3D scenes while moving the camera and the light altogether. In such non-static case, camera poses as well as correspondences between pixels of each frame to apply photometric stereo are required. ORB-SLAM is a technique that can be used to estimate camera poses. To retrieve correspondences, our idea is to start from a sparse 3D mesh obtained with ORB SLAM and then densify the mesh by a plane sweep method using a multi-view photometric consistency. By combining ORB-SLAM and photometric stereo, it is possible to reconstruct dense 3D scenes with a off-the-shelf smartphone and its embedded torchlight. Note that SLAM systems usually struggle with textureless object, which is effectively compensated by the photometric stereo in our method. Experiments are conducted to show that our proposed method gives better results than SLAM alone or COLMAP, especially for partially textureless surfaces.