GAPS: Generator for Automatic Polynomial Solvers
This work is incremental, improving usability and stability for researchers and practitioners in computer vision who need efficient polynomial solvers for minimal problems.
The authors tackled the inefficiency of generating automatic solvers for polynomial equation systems in computer vision by developing GAPS, which wraps and improves an existing tool (autogen) to provide a more user-friendly interface, enhanced functionality, and better stability.
Minimal problems in computer vision raise the demand of generating efficient automatic solvers for polynomial equation systems. Given a polynomial system repeated with different coefficient instances, the traditional Gröbner basis or normal form based solution is very inefficient. Fortunately the Gröbner basis of a same polynomial system with different coefficients is found to share consistent inner structure. By precomputing such structures offline, Gröbner basis as well as the polynomial system solutions can be solved automatically and efficiently online. In the past decade, several tools have been released to generate automatic solvers for a general minimal problems. The most recent tool autogen from Larsson et al. is a representative of these tools with state-of-the-art performance in solver efficiency. GAPS wraps and improves autogen with more user-friendly interface, more functionality and better stability. We demonstrate in this report the main approach and enhancement features of GAPS. A short tutorial of the software is also included.