J
Jacek Komorowski
Researcher at Warsaw University of Technology
Publications - 33
Citations - 227
Jacek Komorowski is an academic researcher from Warsaw University of Technology. The author has contributed to research in topics: Feature (computer vision) & Computer science. The author has an hindex of 5, co-authored 30 publications receiving 67 citations. Previous affiliations of Jacek Komorowski include Maria Curie-Skłodowska University & Military University of Technology in Warsaw.
Papers
More filters
Posted Content
MinkLoc3D: Point Cloud Based Large-Scale Place Recognition
TL;DR: Evaluation on standard benchmarks proves that MinkLoc3D outperforms current state-of-the-art methods for computing a discriminative 3D point cloud descriptor, based on a sparse voxelized point cloud representation and sparse 3D convolutions.
Proceedings ArticleDOI
MinkLoc3D: Point Cloud Based Large-Scale Place Recognition
TL;DR: MinkLoc3D as discussed by the authors is a learning-based method for computing a discriminative 3D point cloud descriptor for place recognition purposes, which is based on a sparse voxelized point cloud representation and sparse 3D convolutions.
Proceedings ArticleDOI
FootAndBall: Integrated Player and Ball Detector.
TL;DR: A deep neural network-based detector dedicated for ball and players detection in high resolution, long shot, video recordings of soccer matches, which has an efficient fully convolutional architecture and can operate on input video stream with an arbitrary resolution.
Proceedings ArticleDOI
MinkLoc++: Lidar and Monocular Image Fusion for Place Recognition
TL;DR: MinkLoc++ as mentioned in this paper is a discriminative multimodal descriptor based on a pair of sensor readings: a point cloud from a LiDAR and an image from an RGB camera, which can be used for place recognition, re-localization and loop closure purposes in robotics or autonomous vehicles applications.
Proceedings ArticleDOI
Improving Point Cloud Based Place Recognition with Ranking-based Loss and Large Batch Training
TL;DR: A simple and effective learning- based method for computing a discriminative 3D point cloud descriptor for place recognition purposes, based on a sparse voxelized representation, enhanced with channel attention blocks.