Temporally Consistent Motion Segmentation from RGB-D Video
This work addresses motion segmentation for computer vision applications, but it appears incremental as it builds on existing rigid motion models with specific improvements.
The paper tackles the problem of motion segmentation in RGB-D video by assuming piecewise rigid motion, resulting in temporally consistent object segmentation and enabling 3D object reconstructions from fused segments.
We present a method for temporally consistent motion segmentation from RGB-D videos assuming a piecewise rigid motion model. We formulate global energies over entire RGB-D sequences in terms of the segmentation of each frame into a number of objects, and the rigid motion of each object through the sequence. We develop a novel initialization procedure that clusters feature tracks obtained from the RGB data by leveraging the depth information. We minimize the energy using a coordinate descent approach that includes novel techniques to assemble object motion hypotheses. A main benefit of our approach is that it enables us to fuse consistently labeled object segments from all RGB-D frames of an input sequence into individual 3D object reconstructions.