This paper presents a method for dense 4D temporal alignment of partial reconstructions of non-rigid surfaces observed from single or multiple moving cameras of complex scenes. 4D Match Trees are introduced for robust global alignment of non-rigid shape based on the similarity between images across sequences and views. Wide-timeframe sparse correspondence between arbitrary pairs of images is established using a segmentation-based feature detector (SFD) which is demonstrated to ive improved matching of non-rigid shape. Sparse SFD correspondence allows the similarity between any pair of image frames to be estimated for moving cameras and multiple views. This enables the 4D Match Tree to be constructed which minimises the observed change in non-rigid shape for global alignment across all images. Dense 4D temporal correspondence across all frames is then estimated by traversing the 4D Match tree using optical ow initialised from the sparse feature matches. The approach is evaluated on single and multiple view images sequences for alignment of partial surface reconstructions of dynamic objects in complex indoor and outdoor scenes to obtain a temporally consistent 4D representation. Comparison to previous 2D and 3D scene ow demonstrates that 4D Match Trees achieve reduced errors due to drift and improved robustness to large non-rigid deformations.


4D Match Trees for Non-rigid Surface Alignment
Armin Mustafa, Hansung Kim and Adrian Hilton
ECCV 2016


Data used in this work can be found in the CVSSP 3D Data Repository.


				title = {4D Match Trees for Non-rigid Surface Alignment},
				author={Mustafa, A. and Kim, H. and Hilton, A.}



This research was supported by the European Commission, FP7 IMPART: Intelligent Management Platform for Advanced Real-time Media Processes project (grant 316564).