Robotics and Computer Vision Laboratory Login  
  Robotics and Computer Vision Laboratory kaist logo
Archive Courses

Home  >  Research  >  Publications

[International Journal] Geometry Guided 3D Propagation for Depth from Small Motion
IEEE Signal Processing Letters , December 2017 [65]
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.
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.


Robotics and Computer Vision Laboratory
KAIST | Electrical Engineering | Contact Us | Sitemap