3D Interest Point Detection via Discriminative Learning
This work addresses the need for flexible and task-specific interest point detection in 3D meshes for applications in computer vision and graphics, representing an incremental improvement over existing geometric methods.
The paper tackles the problem of detecting interest points in 3D meshes by formulating it as a supervised binary classification using a random forest, addressing challenges like imbalanced learning through re-sampling, and validates accuracy by comparing to five state-of-the-art methods on a new benchmark.
The task of detecting the interest points in 3D meshes has typically been handled by geometric methods. These methods, while greatly describing human preference, can be ill-equipped for handling the variety and subjectivity in human responses. Different tasks have different requirements for interest point detection; some tasks may necessitate high precision while other tasks may require high recall. Sometimes points with high curvature may be desirable, while in other cases high curvature may be an indication of noise. Geometric methods lack the required flexibility to adapt to such changes. As a consequence, interest point detection seems to be well suited for machine learning methods that can be trained to match the criteria applied on the annotated training data. In this paper, we formulate interest point detection as a supervised binary classification problem using a random forest as our classifier. Among other challenges, we are faced with an imbalanced learning problem due to the substantial difference in the priors between interest and non-interest points. We address this by re-sampling the training set. We validate the accuracy of our method and compare our results to those of five state of the art methods on a new, standard benchmark.