A robust technique for the estimation of the deformable hyperquadrics from images

Abstract

We present a robust technique for the estimation of deformable hyperquadrics from images. Hyperquadrics are volumetric shape models that include superquadrics as a special case. Recovering hyperquadric parameters is difficult not only due to the existence of many local minima in the error function but also due to the existence of an infinite number of global minima (with zero error) that do not correspond to any meaningful shape. An algorithm that minimizes the error-of-fit function without using techniques similar to those presented here will often find itself stuck in "meaningless" minima, even with good initialization. Our algorithm exhibits good convergence behavior and is largely insensitive to initialization.

Related Papers

• → A Note on the Extended Rosenbrock Function(2006)255 cited
• Local minima in training of deep networks(2017)
• → Local minima in training of neural networks(2016)39 cited
• Faster escaping from local minima for back-propagation algorithm(2008)