Reality Distortion Field Experiment using Machine Learning
Keywords:
Distortion, OpenCV, PyQt, Real-time video manipulation, Spatial, TemporalAbstract
The reality distortion field experiment explores real-time visual manipulation techniques that alter live video feeds to create surreal and immersive experiences. Inspired by the term “reality distortion field,” which describes how perception can be influenced or changed, this project applies machine learning, OpenCV for image processing, and PyQt for an interactive interface to produce dynamic visual effects. These include time-based distortions like freezing and looping, spatial transformations such as motion echoes and gravity shifts, and glitch effects like liquid morphing. The system is designed to be user-friendly, allowing individuals to select and control distortion types dynamically. GPU acceleration, powered by CUDA and OpenGL, ensures high-performance processing for handling complex effects on high-resolution video in real-time. This experiment showcases the creative potential of real-time video manipulation, with applications in digital art, gaming, and augmented reality. By blending machine learning with advanced video processing, the reality distortion field experiment highlights how technology can reshape visual perception for artistic and interactive experiences.
References
R. C. Gonzalez and R. E. Woods, Digital Image Processing. Upper Saddle River, NJ, USA: Pearson Education, 2018.
I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016.
L. Yang, Z. Kong, T. Li, X. Bai, Z. Lin, and H. Cheng, “GPU accelerated color correction and frame warping for real-time video stitching,” arXiv preprint arXiv:2308.09209, Aug. 17, 2023. [Online] Available: https://arxiv.org/abs/2308.09209.
J. D. Hunter, “Matplotlib: A 2D graphics environment,” Comput. Sci. Eng., vol. 9, no. 3, pp. 90–95, May 1, 2007. [Online]. Available: https://www.computer.org/csdl/magazine/cs/2007/03/c3090/13rRUwbJD0A.
I. Janos and W. Benesova, “Single image automatic radial distortion compensation using deep convolutional network,” arXiv preprint arXiv:2112.08198, Dec. 14, 2021. [Online] Available: https://arxiv.org/abs/2112.08198.
M. Cao, S. Yang, Y. Yang, and Y. Zheng, “Rolling shutter correction with intermediate distortion flow estimation,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., 2024, pp. 25338–25347. [Online] Available: https://arxiv.org/html/2404.06350v1.
G. Bradski and A. Kaehler, “OpenCV,” Dr. Dobb’s J. Softw. Tools, vol. 3, no. 2, Nov. 3, 2000. [Online]. Available: http://roswiki.autolabor.com.cn/attachments/Events(2f)ICRA2010Tutorial/ICRA_2010_OpenCV_Tutorial.pdf.
Riverbank Computing, “What is PyQt?” [Online] Available: https://riverbankcomputing.com/software/pyqt/intro.
M. Abadi et al., “TensorFlow: A system for large-scale machine learning,” in Proc. 12th USENIX Symp. Operating Syst. Design Implement. (OSDI 16), 2016, pp. 265–283. [Online]. Available: https://www.usenix.org/conference/osdi16/technical-sessions/presentation/abadi.
C. R. Harris et al., “Array programming with NumPy,” Nature, vol. 585, no. 7825, pp. 357–362, Sep. 17, 2020. [Online] Available: https://www.nature.com/articles/s41586-020-2649-2.
