VSAC: Efficient and Accurate Estimator for H and F
This work addresses the need for efficient and reliable geometry estimation in computer vision applications, representing a substantial incremental improvement over existing methods.
The authors tackled the problem of robust estimation of two-view geometry (homography and fundamental matrix) by introducing VSAC, a RANSAC-type estimator that is significantly faster and highly accurate. Experiments show it runs in 1-2 ms on CPU, is two orders of magnitude faster than MAGSAC++ while matching its precision, and never failed on standard datasets.
We present VSAC, a RANSAC-type robust estimator with a number of novelties. It benefits from the introduction of the concept of independent inliers that improves significantly the efficacy of the dominant plane handling and, also, allows near error-free rejection of incorrect models, without false positives. The local optimization process and its application is improved so that it is run on average only once. Further technical improvements include adaptive sequential hypothesis verification and efficient model estimation via Gaussian elimination. Experiments on four standard datasets show that VSAC is significantly faster than all its predecessors and runs on average in 1-2 ms, on a CPU. It is two orders of magnitude faster and yet as precise as MAGSAC++, the currently most accurate estimator of two-view geometry. In the repeated runs on EVD, HPatches, PhotoTourism, and Kusvod2 datasets, it never failed.