Monocular Dense 3D Reconstruction of a Complex Dynamic Scene from Two Perspective Frames Conference Paper uri icon


  • This paper proposes a new approach for monocular dense 3D reconstruction of a complex dynamic scene from two perspective frames. By applying superpixel over-segmentation to the image, we model a generically dynamic (hence non-rigid) scene with a piecewise planar and rigid approximation. In this way, we reduce the dynamic reconstruction problem to a 3D jigsaw puzzle problem which takes pieces from an unorganized soup of superpixels". We show that our method provides an effective solution to the inherent relative scale ambiguity in structure-from-motion. Since our method does not assume a template prior, or per-object segmentation, or knowledge about the rigidity of the dynamic scene, it is applicable to a wide range of scenarios. Extensive experiments on both synthetic and real monocular sequences demonstrate the superiority of our method compared with the state-of-the-art methods.

name of conference

  • 2017 IEEE International Conference on Computer Vision (ICCV)

published proceedings

  • 2017 IEEE International Conference on Computer Vision (ICCV)

author list (cited authors)

  • Kumar, S., Dai, Y., & Li, H.

citation count

  • 46

complete list of authors

  • Kumar, Suryansh||Dai, Yuchao||Li, Hongdong

publication date

  • October 2017