| Title |
Long Exposure Image Simulation Pipeline using Frame Interpolation Technique |
| Authors |
정경화(Gyeong-Hwa Jeong) ; 이수현(Su-Hyeon Lee) ; 유광석(Kwang-Seok Yoo) ; 이무재(Moo-Jae Lee) |
| DOI |
https://doi.org/10.5573/ieie.2023.60.7.67 |
| Keywords |
Long expolsure photography; Video frame interpolation; Optical flow; Deep learning; Image processing |
| Abstract |
In this paper, we propose a pipeline that combines multiple photos taken consecutively into long exposure images using frame interpolation. In general, in order to take long exposure photos, an ND (Neutral Density) filter attached to the camera lens to adjust the amount of light is required to increase the exposure time. In addition, since elements such as ISO, exposure time, and aperture must be adjusted according to the shooting environment and subject, the skill of the photographer is required. Without these limitations, using a pipeline that uses frame interpolation and fusion with Radiant Amplification, you can achieve similar results to real long-exposure photography even with regular sequentially captured images. |