We present a method to reconstruct dense 3D points from small camera motion. We begin with estimating sparse 3D points and camera poses by Structure from Motion (SfM) method with homography decomposition. Although the estimated points are optimized via bundle adjustment and gives reliable accuracy, the reconstructed points are sparse because it heavily depends on the extracted features of a scene. To handle this, we propose a depth propagation method using both a color prior from the images and a geometry prior from the initial points. The major benefit of our method is that we can easily handle the regions with similar colors but different depths by using the surface normal estimated from the initial points. We design our depth propagation framework into the cost minimization process. The cost function is linearly designed, which makes our optimization tractable. We demonstrate the effectiveness of our approach by comparing with a conventional method using various real-world examples.
Depth from Accidental Motion using Geometry Prior
조회 수 1992 댓글 0
|저 자||Sunghoon Im, Gyeongmin Choe, Hae-Gon Jeon, In So Kweon|
|학 회||IEEE International Conference on Image Processing (ICIP)|
|Notes||This research is supported by the Study on Imaging Systems for the next generation cameras funded by the Samsung Electronics Co., Ltd (DMC R&D center) (IO130806-00717-02).|
Prev Lenticular Lens Parameter Estimation using Single Image for Crosstalk Reduction of Three-dimensional Multi-view Display Lenticular Lens Parameter Estimation using Single Image for Crosstalk Reduction of Three-dimensional Multi-view Display 2015.06.23by 관리자 Reflection Removal using Disparity and Gradient-Sparsity via ... Next Reflection Removal using Disparity and Gradient-Sparsity via ... 2015.05.07by