“…In particular, some techniques tackle the case of open surfaces, where the surface can be entirely observed in at least some frames of the sequence [37,16]. While some work has tackled the more challenging case of volumetric surfaces, most existing methods rely on a pre-processing step, where a 3D model of the object of interest is acquired under rigid, or quasi-rigid motion [17,7,18,35,39,40,42]. While methods relying on quasi-rigidity during this modelbuilding step do account for some degree of deformations, they are very far from attempting to directly estimate the 4D motion of, e.g., a human dancing in front of the sensor.…”