Piecewise Rigid Scene Flow

3D scene flow estimation aims to jointly recover dense geometry and 3D motion from stereoscopic image sequences, thus generalizes classical disparity and 2D optical flow estimation.
To realize its conceptual benefits and overcome limitations of many existing methods, we propose to represent the dynamic scene as a collection of rigidly moving planes, into which the input images are segmented.
Geometry and 3D motion are then jointly recovered alongside an over-segmentation of the scene.
Assuming the rigid motion to persist approximately over time additionally enables us to incorporate multiple frames into the inference.
To that end, each view holds its own representation, which is encouraged to be consistent across all other viewpoints and frames in a temporal window.
We show that such a view-consistent multi-frame scheme significantly improves accuracy, especially in the presence of occlusions, and increases robustness against adverse imaging conditions.

external pageCode availablecall_made

Representative Publications:

• Piecewise Rigid Scene Flow, C. Vogel, K. Schindler, S. Roth, In: International Conference on Computer Vision (ICCV), Sydney, Australia, 2013 Marr Prize Honorable Mention
• 3D Scene Flow with a Piecewise Rigid World Model, C. Vogel, K. Schindler, S. Roth, In: International Journal of Computer Vision (IJCV), Feb. 2015
  

Contact person: external pageChristoph Vogelcall_made