ENHANCING MOTION, A COMPREHENSIVE APPROACH TO VIDEO CREATION FROM STILL IMAGES
Keywords:
Keywords: video interpolation, frame interpolation, object detection, optical flow, motion estimation, post-processing, video encoding, computer vision, video processing.Abstract
Abstract: Creating videos from a sequence of images with moving objects is a complex task that involves several key steps, including object detection/tracking, frame interpolation, post-processing, and video encoding. The thesis provides a detailed algorithm for this process, outlining the steps involved and suggesting specific techniques for each stage. The use of object detection models for tracking objects ensures that the motion in the final video appears smooth and realistic. Frame interpolation, based on optical flow estimation, helps create intermediate frames that bridge the gap between the original frames, enhancing the visual quality of the video. The thesis also emphasizes the importance of post-processing techniques for artifact reduction and visual enhancement. Overall, the thesis provides a comprehensive guide for creating videos from pictures with moving objects, offering valuable insights for researchers and practitioners in the field of computer vision and video processing.
References
Baker, S., Scharstein, D., Lewis, J. P., Roth, S., Black, M. J., & Szeliski, R. (2011). A database and evaluation methodology for optical flow. International Journal of Computer Vision, 92(1), 1-31.
Dosovitskiy, A., Fischer, P., Ilg, E., Hausser, P., Hazirbas, C., Golkov, V., ... & Brox, T. (2015). FlowNet: Learning optical flow with convolutional networks. In Proceedings of the IEEE international conference on computer vision (pp. 2758-2766).
Reda, F. A., Liu, G., Shih, K. J., Wang, T. C., Tao, A., & Catanzaro, B. (2018). Video-to-video synthesis. In Advances in Neural Information Processing Systems (pp. 1199-1208).
Wang, T. C., Liu, M. Y., Zhu, J. Y., Tao, A., Kautz, J., & Catanzaro, B. (2018). High-resolution image synthesis and semantic manipulation with conditional GANs. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 8798-8807).
Xue, T., Wu, J., Bouman, K. L., & Freeman, W. T. (2016). Visual dynamics: Probabilistic future frame synthesis via cross convolutional networks. In Advances in Neural Information Processing Systems (pp. 91-99).
