Refine
Year of publication
Document Type
- Article (599)
- Part of a Book (526)
- Conference Proceeding (435)
- Workingpaper / Report (232)
- Article trade magazine (99)
- Announcement (75)
- Book (68)
- Collection (65)
- Part of Periodical (43)
- Preprint (20)
Language
Is part of the Bibliography
- yes (2233) (remove)
Keywords
- FBSK_Webseite (328)
- FHD (148)
- Forena (121)
- Luftreinhaltung (89)
- Rechtsradikalismus (54)
- Sozialarbeit (51)
- Innovation (47)
- VSVR (43)
- Messtechnik (42)
- Numerische Strömungssimulation (35)
Department/institution
- Fachbereich - Sozial- & Kulturwissenschaften (762)
- Fachbereich - Maschinenbau und Verfahrenstechnik (528)
- Fachbereich - Medien (359)
- Fachbereich - Wirtschaftswissenschaften (268)
- Creative Media Production and Entertainment Computing (126)
- Hochschulverwaltung (97)
- Fachbereich - Elektro- & Informationstechnik (93)
- Fachbereich - Design (49)
- Sound and Vibration Engineering (44)
- Digital Learning and Digital Literacy (37)
Physically grounded PSF-based image degradation is necessary for studying optics-related object-detector robustness, but existing workflows typically rely on offline dataset generation and integrate poorly with GPU-resident frameworks such as MMDetection. We present CIDPL, a CUDA-accelerated Python library that adapts our standalone Image Degradation Application (IDA) into a real-time, framework-integrated pipeline for MMDetection. CIDPL couples Python and C++ via PyBind11, performs degradation directly on GPU tensors in the DataPreprocessor, and organizes multiple optical variants in a traceable Super-Batch format. Numerical validation shows exact agreement with IDA for TIFF inputs, while optical validation reproduces KrakenOS-based SFR trends. In throughput tests, CIDPL improves mean degradation speed over IDA by 4.7x on a single GPU and 7.6x on two GPUs, enabling real-time processing at 117 FPS with negligible overhead during both training and inference. KITTI experiments further show that the integration enables practical detector-level robustness studies under varying defocus conditions