http://ieeexplore.ieee.org/document/8063412/In this letter, we present an accurate Depth from Small Motion approach, which reconstructs three-dimensional (3-D) depth from image sequences with extremely narrow base-lines.We start with estimating sparse 3-D points and camera poses via the structure from motion method. For dense depth reconstruction, we propose a novel depth propagation using a geometric guidance term that considers not only the geometric constraint from the surface normal, but also color consistency. In addition, we propose an accurate surface normal estimation method with a multiple range search so that the normal vector can guide the direction of the depth propagation precisely. The major benefit of our depth propagation method is that it obtains detailed structures of a scene without fronto-parallel bias.We validate our method using various indoor and outdoor datasets, and both qualitative and quantitative experimental results show that our new algorithm consistently generates better 3-D depth information than the results of existing state-of-the-art methods.
조회 수 134 댓글 0
|저 자||Seunghak Shin, Sunghoon Im, Inwook Shim, Hae-Gon Jeon, In So Kweon|
|학 회||IEEE Signal Processing Letters|
|Notes||This work was supported by the “Development of core technology for advanced locomotion/manipulation based on high-speed/power robot platform and robot intelligence,” project from the Korea Evaluation Institute of Industrial Technology of the Republic of Korea. The work of S. Im and H.-G. Jeon was supported in part by Global Ph.D. Fellowship Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education under Grant NRF-2016907531 and Grant NRF-2015034617.|
Prev Robust and Globally Optimal Manhattan Frame Estimation in Near Real Time Robust and Globally Optimal Manhattan Frame Estimation in Near Real Time 2017.11.06by 관리자 Intelligent Assistant for People with Low Vision Abilities Next Intelligent Assistant for People with Low Vision Abilities 2017.09.18by