Comenius University Bratislava

Robust Self-Calibration of Focal Lengths from the Fundamental Matrix
The problem of self-calibration of two cameras from a given fundamental matrix is one of the basic problems in geometric computer …
Cite DOI
Sketch it for the Robot! How Child-Like Robots' Joint Attention Affects Humans' Drawing Strategies
The work proposes investigating drawing activities in interactive contexts to shed light on the links between socio-cognitive and …
Cite DOI
Enhancement of 3D Camera Synthetic Training Data with Noise Models
The goal of this paper is to assess the impact of noise in 3D camera-captured data by modeling the noise of the imaging process and …
Cite DOI
Appearance-Based Gaze Estimation Enhanced with Synthetic Images Using Deep Neural Networks
Human eye gaze estimation is an important cognitive ingredient for successful human-robot interaction, enabling the robot to read and …
PDF Cite DOI
Evaluating the Significance of Outdoor Advertising from Driver’s Perspective Using Computer Vision
Outdoor advertising, such as roadside billboards, plays a significant role in marketing campaigns but can also be a distraction for …
Cite DOI
Processing and Segmentation of Human Teeth from 2D Images using Weakly Supervised Learning
Teeth segmentation is an essential task in dental image analysis for accurate diagnosis and treatment planning. While supervised deep …
Cite DOI
Supersampling of Data from Structured-light Scanner with Deep Learning
This paper focuses on increasing the resolution of depth maps obtained from 3D cameras using structured light technology. Two deep …
Cite DOI
Tuning-less Object Naming with a Foundation Model
We implement a real-time object naming system that enables learning a set of named entities never seen. Our approach employs an …
PDF DOI arXiv
Novel Synthetic Data Tool for Data-Driven Cardboard Box Localization
Application of neural networks in industrial settings, such as automated factories with bin-picking solutions requires costly …
DOI ICANN 2023
QuasiNet: a Neural Network with Trainable Product Layers
Classical neural networks achieve only limited convergence in hard problems such as XOR or parity when the number of hidden neurons is …
DOI ICANN 2023