"Maximizing rigidity" revisited: a convex programming approach for generic 3D shape reconstruction from multiple perspective views
This provides a unified method for 3D reconstruction that handles both rigid and non-rigid scenes, addressing a long-standing separation in the field, though it appears incremental as it builds on prior work.
The paper tackled the problem of unifying rigid and non-rigid structure-from-motion for 3D shape reconstruction from multiple views by developing a convex programming approach based on maximizing rigidity, achieving state-of-the-art accuracy.
Rigid structure-from-motion (RSfM) and non-rigid structure-from-motion (NRSfM) have long been treated in the literature as separate (different) problems. Inspired by a previous work which solved directly for 3D scene structure by factoring the relative camera poses out, we revisit the principle of "maximizing rigidity" in structure-from-motion literature, and develop a unified theory which is applicable to both rigid and non-rigid structure reconstruction in a rigidity-agnostic way. We formulate these problems as a convex semi-definite program, imposing constraints that seek to apply the principle of minimizing non-rigidity. Our results demonstrate the efficacy of the approach, with state-of-the-art accuracy on various 3D reconstruction problems.