TY - GEN
T1 - Monocular Dense 3D Reconstruction of a Complex Dynamic Scene from Two Perspective Frames
AU - Kumar, Suryansh
AU - Dai, Yuchao
AU - Li, Hongdong
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/12/22
Y1 - 2017/12/22
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85041912405&partnerID=8YFLogxK
U2 - 10.1109/ICCV.2017.498
DO - 10.1109/ICCV.2017.498
M3 - Conference contribution
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 4659
EP - 4667
BT - Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 16th IEEE International Conference on Computer Vision, ICCV 2017
Y2 - 22 October 2017 through 29 October 2017
ER -