Monocular Dense 3D Reconstruction of a Complex Dynamic Scene from Two Perspective Frames
It addresses the problem of 3D reconstruction from monocular video for applications like robotics or AR, but it is incremental as it builds on existing dynamic scene reconstruction approaches.
The paper tackles monocular dense 3D reconstruction of complex dynamic scenes from two frames by modeling scenes with piecewise planar and rigid superpixels, reducing it to a '3D jigsaw puzzle' problem, and it demonstrates superiority over state-of-the-art methods in experiments.
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.