Progressive NAPSAC: sampling from gradually growing neighborhoods
This work addresses the problem of faster robust estimation for computer vision tasks, but it is incremental as it builds on existing methods like NAPSAC and USAC.
The authors tackled the problem of robust geometric model fitting (homography and fundamental matrix) by proposing Progressive NAPSAC, which samples from gradually growing neighborhoods to find local structures earlier, and integrated it into an improved USAC* pipeline. The result showed that USAC* with P-NAPSAC outperformed reference methods in speed on all tested problems across 10,691 models from seven datasets.
We propose Progressive NAPSAC, P-NAPSAC in short, which merges the advantages of local and global sampling by drawing samples from gradually growing neighborhoods. Exploiting the fact that nearby points are more likely to originate from the same geometric model, P-NAPSAC finds local structures earlier than global samplers. We show that the progressive spatial sampling in P-NAPSAC can be integrated with PROSAC sampling, which is applied to the first, location-defining, point. P-NAPSAC is embedded in USAC, a state-of-the-art robust estimation pipeline, which we further improve by implementing its local optimization as in Graph-Cut RANSAC. We call the resulting estimator USAC*. The method is tested on homography and fundamental matrix fitting on a total of 10,691 models from seven publicly available datasets. USAC* with P-NAPSAC outperforms reference methods in terms of speed on all problems.