P
Pranav Kadam
Researcher at University of Southern California
Publications - 10
Citations - 208
Pranav Kadam is an academic researcher from University of Southern California. The author has contributed to research in topics: Point cloud & Feature extraction. The author has an hindex of 5, co-authored 10 publications receiving 73 citations.
Papers
More filters
Journal ArticleDOI
PointHop: An Explainable Machine Learning Method for Point Cloud Classification
TL;DR: It is shown by experimental results that the PointHop method offers classification performance that is comparable with state-of-the-art methods while demanding much lower training complexity.
Proceedings ArticleDOI
Pointhop++: A Lightweight Learning Model on Point Sets for 3D Classification
TL;DR: The PointHop++ method is improved in two aspects: reducing its model complexity in terms of the model parameter number and ordering discriminant features automatically based on the cross-entropy criterion, which is essential for wearable and mobile computing.
Posted Content
R-PointHop: A Green, Accurate and Unsupervised Point Cloud Registration Method.
TL;DR: R-PointHop as discussed by the authors determines a local reference frame (LRF) for every point using its nearest neighbors and finds its local attributes by point downsampling, neighborhood expansion, attribute construction and dimensionality reduction steps.
Proceedings ArticleDOI
Unsupervised Point Cloud Registration via Salient Points Analysis (SPA)
TL;DR: Li et al. as mentioned in this paper proposed an unsupervised point cloud registration method, called salient points analysis (SPA), which can register two point clouds effectively using only a small subset of salient points.
Proceedings ArticleDOI
Unsupervised Feedforward Feature (UFF) Learning for Point Cloud Classification and Segmentation
TL;DR: In this article, an unsupervised feed-forward feature (UFF) learning scheme for joint classification and segmentation of 3D point clouds is proposed. But the UFF method does not exploit the statistical correlations of points in a point cloud set to learn shape and point features in a one-pass feedforward manner.