Conference Agenda
Overview and details of the sessions of this conference. Please select a date or location to show only sessions at that day or location. Please select a single session for detailed view (with abstracts and downloads if available).
Please note that all times are shown in the time zone of the conference. The current conference time is: 15th Sept 2026, 10:38:22am EEST
External resources will be made available 5 min before a session starts. You may have to reload the page to access the resources.
|
Daily Overview |
| Session | |
|
STE-R PS6: Remote Session 6 Location: online Session Chair: Marcel Freimuth, University of Wuppertal Session Chair: Christian Sauder, University of Wuppertal | |
    | |
9:51am - 10:06am
Leveraging Adjacent Information in DNNs for Image Denoising 1: Department of Applied Mathematics, National University of Science and Technology POLITEHNICA Bucharest, Romania; 2: Faculty of Electrical Engineering, National University of Science and Technology POLITEHNICA Bucharest, Romania; 3: Faculty of Electrical Engineering and Computer Science Transilvania University of Brasov, Romania; 4: Karlsruhe Institute of Technology: Karlsruhe, Baden-Wurttemberg, Deutschland; 5: Center for Research and Training in Innovative Techniques of Applied Mathematics in Engineering, National University of Science and Technology POLITEHNICA Bucharest, Romania Deep Neural Networks (DNNs) are deep learning models inspired by biological neural networks, used for complex pattern recognition, visual and auditory data processing, and multidimensional signal interpretation. They have become fundamental in areas such as image recognition, natural language processing, time series prediction, and industrial process optimization. Denoising represents a central application of DNNs, with the role of highlighting hidden structures and increasing the accuracy of analysis. Noise can be introduced by external factors (lighting conditions, mechanical vibrations, electromagnetic variations) or internal (measurement errors, instrumentation limitations). Its reduction allows: identifying defects at a microscopic scale, improving the reliability of communications, ensuring data security, and optimizing visual processing. The goal of using DNNs in denoising is to exploit their generalization and adaptability to achieve high performance with low data collection costs. | |
